Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Memory (Artificial).
Дисертації з теми "Memory (Artificial)"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Memory (Artificial)".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Hedberg, Charlie Forsberg, and Alexander Pedersen. "Artificial Intelligence : Memory-driven decisions in games." Thesis, Blekinge Tekniska Högskola, Institutionen för teknik och estetik, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-3640.
Повний текст джерелаАнотація:
Developing AI (Artificial Intelligence) for games can be a hard and challenging task. It is sometimes desired to create behaviors that follow some sort of logical pattern. In order to do this, information must be gathered and processed. This bachelor thesis presents an algorithm that could assist current AI technologies to collect and memorize environmental data. The thesis also covers practical implementation guidelines, established through research and testing.<br>Att utveckla AI (Artificiell Intelligence) i spel kan vara en hård och utmanande uppgift. Ibland är det önskvärt att skapa beteenden som följer något sorts logiskt mönster. För att kunna göra detta måste information samlas in och processas. I detta kandidatarbete presenteras en algoritm som kan assistera nuvarande AI-teknologier för att samla in och memorera omgivningsinformation. Denna uppsats täcker också riktlinjer för praktisk implementering fastställda genom undersökning och tester.<br>Detta är en reflekstionsdel till en digital medieproduktion.
2
Bachhav, Pramod. "Explicit memory inclusion for efficient artificial bandwidth extension." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS492.
Повний текст джерелаАнотація:
La plupart des algorithmes ABE exploitent les informations contextuelles ou la mémoire capturée via l'utilisation de caractéristiques statiques ou dynamiques extraites de trames de parole voisines. L'utilisation de la mémoire entraîne des caractéristiques dimensionnelles plus élevées et une complexité informatique accrue. Lorsque les informations provenant de trames de prévisualisation sont également utilisées, la latence augmente également. Les travaux antérieurs montrent l'avantage pour ABE d'exploiter la mémoire sous la forme d'entités dynamiques avec un modèle de régression standard. Même dans ce cas, la littérature manque d'une analyse quantitative de l'avantage relatif de l'inclusion de mémoire explicite. La recherche présentée dans cette thèse évalue dans quelle mesure la mémoire explicite est utile et rapporte en outre un certain nombre de techniques différentes qui permettent son inclusion sans augmentation significative de la latence et de la complexité de calcul. Les avantages sont démontrés à la fois par une analyse quantitative avec une mesure basée sur la théorie de l'information et par des tests d'écoute subjectifs. Les principales contributions concernent la préservation de l'efficacité des calculs grâce à l'utilisation de la réduction de dimensionnalité sous la forme d'une analyse en composantes principales, d'auto-encodeurs superposés semi-supervisés et d'auto-encodeurs variationnels conditionnels. Les deux dernières techniques optimisent la réduction de la dimensionnalité pour offrir une performance ABE supérieure<br>Most ABE algorithms exploit contextual information or memory captured via the use of static or dynamic features extracted from neighbouring speech frames. The use of memory leads to higher dimensional features and increased computational complexity. When information from look-ahead frames is also utilised, then latency also increases. Past work points toward the benefit to ABE of exploiting memory in the form of dynamic features with a standard regression model. Even so, the literature is missing a quantitative analysis of the relative benefit of explicit memory inclusion. The research presented in this thesis assesses the degree to which explicit memory is of benefit and furthermore reports a number of different techniques that allow for its inclusion without significant increases to latency and computational complexity. Benefits are shown through both a quantitative analysis with an information-theoretic measure and subjective listening tests. Key contributions relate to the preservation of computational efficiency through the use of dimensionality reduction in the form of principal component analysis, semisupervised stacked autoencoders and conditional variational auto-encoders. The two latter techniques optimise dimensionality reduction to deliver superior ABE performance
3
Kanar, Ege. "Photography as artificial memory: Construction of the Photographic Self." Master's thesis, Akademie múzických umění v Praze. Filmová a televizní fakulta AMU. Knihovna, 2008. http://www.nusl.cz/ntk/nusl-78095.
Повний текст джерела
4
Moposita, Tatiana. "Artificial Neural Network (ANN) design using Compute-in-Memory." Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS682.
Повний текст джерелаАнотація:
De nos jours, l'ère du " More than Moore" a émergé comme une influence significative face aux limitations anticipées par la loi de Moore. Les systèmes informatiques explorent des technologies alternatives pour maintenir et améliorer les performances. Cette idée émergé pour résoudre les défis des systèmes électroniques inspirés des réseau biologiques, communément appelés Réseau Neurones Artificiels (ANN). L'utilisation des technologies emerging non-volatile memory (eNVM) est étudiée comme des alternatives prometteuses. Ces technologies offrent plusieurs avantages par rapport à la technologie CMOS traditionnelle, tels qu'une vitesse accrue, des densités plus élevées et une consommation d'énergie moindre. En conséquence, Compute-in-memory utilise les eNVM pour effectuer des calculs directement dans la mémoire, augmentant ainsi la capacité de mémoire et la vitesse de traitement. L'objectif de cette thèse se concentre sur la recherche de la conception de Réseau Neurones Artificiels en utilisant Compute-in-Memory, en employant des solutions matérielles efficaces pour les ANNs tant au niveau du circuit qu'au niveau de l'architecture. Les travaux de recherche récents dans ce contexte ont proposé des conceptions de circuits très efficaces pour optimiser les besoins de calcul énormes nécessaires au traitement des données par les ANNs. Ainsi, pour explorer les capacités d'un ANN au niveau du nœud de sortie, la conception de fonctions d'activation a été proposée. La sélection d'une fonction d'activation est significative car elle détermine la puissance et les capacités du réseau neuronal, et la précision des prédictions dépend principalement de ce choix. Pour évaluer l'efficacité d'une fonction d'activation conçue pour une implémentation analogique, les fonctions d'activation sigmoïde et softmax sont proposées. Cette thèse explore l'intégration de dispositifs mémoires émergents tels que la Spin-Transfer-Torque Magnetic Random Access Memory (STT-MRAM) avec la technologie CMOS. Cette approche combinée vise à tirer parti de la capacité intrinsèque de l'informatique en mémoire offerte par ces dispositifs. Perpendicular magnetic tunneling junction (MTJ) et des FinFET ont été pris en compte pour cette étude. Single-barrier (SMTJ) et double-barrier (DMTJ) sont considérés pour évaluer l'impact de la cellule STT-MRAM basée sur DMTJ par rapport à son homologue SMTJ conventionnel sur les performances d'un réseau neuronal à perceptrons multicouches (MLP) à deux couches. L'évaluation a été réalisée au moyen d'un cadre de simulation personnalisé, de niveaux de dispositif et de cellule jusqu'aux niveaux d'architecture mémoire et d'algorithme. De plus, pour améliorer l'efficacité énergétique d'une architecture Logic-in-Memory (LIM) basée sur les dispositifs STT-MTJ, une nouvelle architecture (SIMPLY+) issue de la logique Smart Material Implication (SIMPLY) et des technologies STT-MRAM basées sur MTJ perpendiculaires a été développée. Le schéma SIMPLY+ constitue une solution prometteuse pour le développement d'architectures informatiques en mémoire économes en énergie et fiables. Toutes les solutions de circuits ont été évaluées à l'aide de simulateurs de circuits commerciaux (par exemple, Cadence Virtuoso). L'activité de conception de circuits impliquant des dispositifs mémoires émergents a également nécessité l'utilisation et le calibrage de modèles compacts basés sur Verilog-A pour intégrer le comportement de ces dispositifs dans l'outil de conception de circuits. Les solutions présentées dans cette thèse impliquent des techniques qui offrent des avancées significatives pour les futures applications. Du point de vue de la conception, l'intégration de modules logiques avec la mémoire STT-MRAM est très réalisable en raison de la compatibilité transparente entre les STT-MRAM et les circuits CMOS. Cette approche est non seulement avantageuse pour la technologie CMOS standard, mais elle exploite également le potentiel des technologies émergentes<br>Nowadays, the era of ”More than Moore” has arisen as a significant influence in light of the limitations anticipated by Moore’s law. The computing systems are exploring alternative technologies to sustain and enhance performance improvements. The idea of alternative innovative technologies has emerged in solving challenges of electronic systems inspired by biological neural networks, commonly referred to as Artificial Neural Network (ANN). The use of emerging non-volatile memory (eNVM) technologies are being explored as promising alternatives. These technologies offer several advantages over traditional CMOS technology, such as increased speed, higher densities, and lower power consumption. As a result, Compute-in-memory employs eNVMs to perform computation within the memory itself, hence increasing memory capacity and processing speed. The objective of this thesis focuses on the research of Artificial Neural Networks design using Compute in Memory, by employing efficient hardware solutions for ANNs at both circuit- and architecture-level. Recent research work in this context has proposed very efficient circuit designs to optimize the enormous computational needs required by data processing by ANNs. Therefore, to explore the capabilities of an ANN at the output node, the design of activation functions were proposed. The selection of an activation function is significant as it determines the power and capabilities of the neural network, and the accuracy of predictions is primarily dependent on this choice. To assess the effectiveness of an activation function designed for analog implementation, the sigmoid and the softmax activation function are proposed. Besides, this thesis explores the integration of emerging memory devices like Spin-Transfer-Torque Magnetic Random Access Memory (STT-MRAM) with CMOS technology. This combined approach aims to leverage the intrinsic capability of in-memory computing offered by these devices. STT-MRAMs based on state-of-the-art perpendicular magnetic tunneling junction (MTJ) and FinFETs has been considered for this study. Single-barrier magnetic tunnel junction (SMTJ) and double-barrier magnetic tunnel junction (DMTJ) devices are considered to evaluate the impact of STT-MRAM cell based on DMTJ against the conventional SMTJ counterpart on the performance of a two-layer multilayer perceptron (MLP) neural network. The assessment was carried out through a customized simulation framework from device and bitcell levels to memory architecture and algorithm levels. Moreover, to improve the energy-efficiency of a Logic-in-Memory (LIM) architecture based on STT-MTJ devices, a new architecture (SIMPLY+) from the Smart Material Implication (SIMPLY) logic and perpendicular MTJ based STT-MRAM technologies was developed. The SIMPLY+ scheme is a promising solution for the development of energy-efficient and reliable in-memory computing architectures. All circuit solutions were evaluated using commercial circuit simulators (e.g. Cadence Virtuoso). Circuit design activity involving emerging memory devices also required the use and calibration of Verilog-A based compact models to integrate the behavior of such devices into the circuit design tool. The solutions presented in this thesis involve techniques that offer significant advancements for future applications. From a design perspective, the integration of logic modules with STT-MRAM memory is highly feasible due to the seamless compatibility between STT-MRAMs and CMOS circuits. This approach not only proves advantageous for standard CMOS technology but also leverages the potential of emerging technologies
5
Day, Jonathan. ""Must I remember?" : artificial memory systems and early modern England." Thesis, University of Liverpool, 2014. http://livrepository.liverpool.ac.uk/2006202/.
Повний текст джерелаАнотація:
My thesis traces the evolution of artificial memory systems from classical Greece to early modern England to explore memorial traumas and the complex nature of a very particular way of remembering. An artificial memory system is a methodology to improve natural memory. Classical artificial memory systems employ an architectural metaphor, emphasising regularity and striking imagery. Classical memory systems also frequently describe the memory as a blank page. This thesis follows the path of transmission of these ideas and the perennial relationship between memory and forgetting and memory and fiction, as well as the constant threat of memorial collapse.
6
Ludwig, Lars [Verfasser], and Thomas [Akademischer Betreuer] Lachmann. "Extended Artificial Memory. Toward an integral cognitive theory of memory and technology / Lars Ludwig. Betreuer: Thomas Lachmann." Kaiserslautern : Technische Universität Kaiserslautern, 2013. http://d-nb.info/1045194794/34.
Повний текст джерела
7
Ntourntoufis, Panayotis. "Aspects of the theory of weightless artificial neural networks." Thesis, Imperial College London, 1994. http://hdl.handle.net/10044/1/8506.
Повний текст джерела
8
Turvey, Simon Paul. "Analysing and enhancing the performance of associative memory architectures." Thesis, University of Hertfordshire, 2003. http://hdl.handle.net/2299/14113.
Повний текст джерелаАнотація:
This thesis investigates the way in which information about the structure of a set of training data with 'natural' characteristics may be used to positively influence the design of associative memory neural network models of the Hopfield type. This is done with a view to reducing the level of connectivity in models of this type. There are three strands to this work. Firstly, an empirical evaluation of the implementation of existing theory is given. Secondly, a number of existing theories are combined to produce novel network models and training regimes. Thirdly, new strategies for constructing and training associative memories based on knowledge of the structure of the training data are proposed. The first conclusion of this work is that, under certain circumstances, performance benefits may be gained by establishing the connectivity in a non-random fashion, guided by the knowledge gained from the structure of the training data. These performance improvements exist in relation to networks in which sparse connectivity is established in a purely random manner. This dilution occurs prior to the training of the network. Secondly, it is verified that, as predicted by existing theory, targeted post-training dilution of network connectivity provides greater performance when compared with networks in which connections are removed at random. Finally, an existing tool for the analysis of the attractor performance of neural networks of this type has been modified and improved. Furthermore, a novel, comprehensive performance analysis tool is proposed.
9
Tigreat, Philippe. "Sparsity, redundancy and robustness in artificial neural networks for learning and memory." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2017. http://www.theses.fr/2017IMTA0046/document.
Повний текст джерелаАнотація:
L'objectif de la recherche en Intelligence Artificielle (IA) est de répliquer les capacités cognitives humaines au moyen des ordinateurs modernes. Les résultats de ces dernières années semblent annoncer une révolution technologique qui pourrait changer profondément la société. Nous focalisons notre intérêt sur deux aspects cognitifs fondamentaux, l'apprentissage et la mémoire. Les mémoires associatives offrent la possibilité de stocker des éléments d'information et de les récupérer à partir d'une partie de leur contenu, et imitent ainsi la mémoire cérébrale. L'apprentissage profond permet de passer d'une perception analogique du monde extérieur à une représentation parcimonieuse et plus compacte. Dans le chapitre 2, nous présentons une mémoire associative inspirée des réseaux de Willshaw, avec une connectivité contrainte. Cela augmente la performance de récupération des messages et l'efficacité du stockage de l'information.Dans le chapitre 3, une architecture convolutive a été appliquée sur une tâche de lecture de mots partiellement affichés dans des conditions similaires à une étude de psychologie sur des sujets humains. Cette expérimentation montre la similarité de comportement du réseau avec les sujets humains concernant différentes caractéristiques de l'affichage des mots.Le chapitre 4 introduit une méthode de représentation des catégories par des assemblées de neurones dans les réseaux profonds. Pour les problèmes à grand nombre de classes, cela permet de réduire significativement les dimensions d'un réseau.Le chapitre 5 décrit une méthode d'interfaçage des réseaux de neurones profonds non supervisés avec les mémoires associatives à cliques<br>The objective of research in Artificial Intelligence (AI) is to reproduce human cognitive abilities by means of modern computers. The results of the last few years seem to announce a technological revolution that could profoundly change society. We focus our interest on two fundamental cognitive aspects, learning and memory. Associative memories offer the possibility to store information elements and to retrieve them using a sub-part of their content, thus mimicking human memory. Deep Learning allows to transition from an analog perception of the outside world to a sparse and more compact representation.In Chapter 2, we present a neural associative memory model inspired by Willshaw networks, with constrained connectivity. This brings an performance improvement in message retrieval and a more efficient storage of information.In Chapter 3, a convolutional architecture was applied on a task of reading partially displayed words under similar conditions as in a former psychology study on human subjects. This experiment put inevidence the similarities in behavior of the network with the human subjects regarding various properties of the display of words.Chapter 4 introduces a new method for representing categories usingneuron assemblies in deep networks. For problems with a large number of classes, this allows to reduce significantly the dimensions of a network.Chapter 5 describes a method for interfacing deep unsupervised networks with clique-based associative memories
10
Church, Dana L. "Spatial encoding of artificial flowers by bumblebees (Bombus impatiens): The contents of memory." Thesis, University of Ottawa (Canada), 2005. http://hdl.handle.net/10393/29206.
Повний текст джерелаАнотація:
A novel methodology allowed simultaneous investigation of three elements of bumblebee foraging behaviour: spatial encoding of flower position, landmark use, and scent marking. Bumblebees were presented with a row of artificial flowers in a flight cage, one flower offering reward (S+). Testing involved empty (i.e., unrewarding) flowers. In Experiment 1, flower covers presumed to be scent marked (old covers) were switched with one of the unmarked covers, or replaced with new, scent-mark-free covers. Results confirmed previous research: presence of old covers influenced response type rather than floral choice. Choice appeared to have been made using memory. In Experiment 2, the S- were moved during testing to change the relative position of the S+. New covers were used for half of the bees. The flower in the same absolute position (wrong relative position) as the S+ was consistently chosen, suggesting that the S- did not function as landmarks. Contrary to Experiment 1, old covers influenced flower choice. Experiment 3 replicated Experiments 1 and 2. Again, bees preferred absolute position, but results suggest relative position was encoded and influenced choice under certain circumstances. The effect of old vs. new covers continued to be inconsistent: choice means were higher with new covers, and probing often occurred on new covers. Finally, when flower array independent (FAI) information and memory for a flight vector were placed in conflict in Experiment 4, bees showed a bias for using FAI cues. Taken together, these experiments show that the definition of a landmark remains to be clarified, the role of scent marking remains elusive, and bumblebees showed a consistent bias for using FAI information to locate a goal. Contributions of this thesis are placed within the context of research with vertebrate species and natural bumblebee foraging behaviour.
11
Heyder, Jakob. "Hierarchical Temporal Memory Software Agent : In the light of general artificial intelligence criteria." Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-75868.
Повний текст джерелаАнотація:
Artificial general intelligence is not well defined, but attempts such as the recent listof “Ingredients for building machines that think and learn like humans” are a startingpoint for building a system considered as such [1]. Numenta is attempting to lead thenew era of machine intelligence with their research to re-engineer principles of theneocortex. It is to be explored how the ingredients are in line with the design princi-ples of their algorithms. Inspired by Deep Minds commentary about an autonomy-ingredient, this project created a combination of Numentas Hierarchical TemporalMemory theory and Temporal Difference learning to solve simple tasks defined in abrowser environment. An open source software, based on Numentas intelligent com-puting platform NUPIC and Open AIs framework Universe, was developed to allowfurther research of HTM based agents on customized browser tasks. The analysisand evaluation of the results show that the agent is capable of learning simple tasksand there is potential for generalization inherent to sparse representations. However,they also reveal the infancy of the algorithms, not capable of learning dynamic com-plex problems, and that much future research is needed to explore if they can createscalable solutions towards a more general intelligent system.
12
Hågbäck, Moa. "Artificially Authentic and Authentically Artificial : Experiencing the body of the past through the affect of the transmedial narrative of the Outlander-story world." Thesis, Linnéuniversitetet, Institutionen för kulturvetenskaper (KV), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-86157.
Повний текст джерелаАнотація:
Målet och syftet med denna studie är att observera, tolka, och vidareutveckla förståelsen för den samtida turistens interagerande med, och omförhandlande av, det historiska rummet genom individualistisk påverkan från fiktiva narrativ – i detta fallet, Outlanders transmediala berättelsevärld. Genom ett teoretiskt ramverk uppbyggt på materialism, påverkan, tidsresande och proteser har jag analyserat och kartlagt både kulturarvsplatserna samt Outlander-fansens interaktion med dessa genom att ha deltagit själv i två guidade endagarsturer, samt genom en djupgående, om än liten, enkät. I en nutid som beskådar hur förhållandet till det förflutna och de platser som kopplas till de temporala och spatiala dimensionerna av historien förändras snabbt och omgående, är detta projekt avgörande för att vidare förstå denna minneskultur och vidareutvecklandet av ett kollektivt minne. Resultatet av mina observationer och min enkät påvisar och demonstrerar hur omfattande individuell den sensoriska upplevelsen har blivit inom Outlander-turismen i Skottland. Genom metoder såsom påverkan och lekfullhet är besökaren inbjuden till att tolka platserna i syfte att tillfredsställa deras personliga behov för autencitet i både fiktionen, historien, och sensationen. Ändock är inte vikten av, och värdet på, historien helt och hållet förlorad; majoriteten av respondenterna demonstrerar ett ökat intresse till den faktiska historien, den ’riktiga’ och autentiska, samtidigt som de återinvesterar i det ’virtuella’ och artificiella. Att bära historiens fysiska kropp som en protes, fullständigt beroende av narrativets påverkan, manifesterar den sensoriska upplevelsen och det fysiska mötet med rummet som en anpassad sammangjutning mellan historien och kroppen; besittningen av den historiska protesen stör fördelaktigt ej den egna kroppens integritet
13
Brogliato, Marcelo Salhab. "Understanding the critical distance in sparse distributed memory." reponame:Repositório Institucional do FGV, 2012. http://hdl.handle.net/10438/13095.
Повний текст джерелаАнотація:
Submitted by Marcelo Salhab Brogliato (msbrogli@gmail.com) on 2015-01-05T20:39:25Z
No. of bitstreams: 1
!FullThesis-v6 -biblioteca-digital.pdf: 64255589 bytes, checksum: 0ca16d02e6d615b8fc4c6f4f46db2c22 (MD5)<br>Approved for entry into archive by ÁUREA CORRÊA DA FONSECA CORRÊA DA FONSECA (aurea.fonseca@fgv.br) on 2015-01-06T12:52:32Z (GMT) No. of bitstreams: 1
!FullThesis-v6 -biblioteca-digital.pdf: 64255589 bytes, checksum: 0ca16d02e6d615b8fc4c6f4f46db2c22 (MD5)<br>Approved for entry into archive by Marcia Bacha (marcia.bacha@fgv.br) on 2015-01-12T12:15:58Z (GMT) No. of bitstreams: 1
!FullThesis-v6 -biblioteca-digital.pdf: 64255589 bytes, checksum: 0ca16d02e6d615b8fc4c6f4f46db2c22 (MD5)<br>Made available in DSpace on 2015-01-12T12:16:51Z (GMT). No. of bitstreams: 1
!FullThesis-v6 -biblioteca-digital.pdf: 64255589 bytes, checksum: 0ca16d02e6d615b8fc4c6f4f46db2c22 (MD5)
Previous issue date: 2012-02-02<br>Modelos de tomada de decisão necessitam refletir os aspectos da psi- cologia humana. Com este objetivo, este trabalho é baseado na Sparse Distributed Memory (SDM), um modelo psicologicamente e neuro- cientificamente plausível da memória humana, publicado por Pentti Kanerva, em 1988. O modelo de Kanerva possui um ponto crítico: um item de memória aquém deste ponto é rapidamente encontrado, e items além do ponto crítico não o são. Kanerva calculou este ponto para um caso especial com um seleto conjunto de parâmetros (fixos). Neste trabalho estendemos o conhecimento deste ponto crítico, através de simulações computacionais, e analisamos o comportamento desta 'Critical Distance' sob diferentes cenários: em diferentes dimensões; em diferentes números de items armazenados na memória; e em diferentes números de armazenamento do item. Também é derivada uma função que, quando minimizada, determina o valor da 'Critical Distance' de acordo com o estado da memória. Um objetivo secundário do trabalho é apresentar a SDM de forma simples e intuitiva para que pesquisadores de outras áreas possam imaginar como ela pode ajudá-los a entender e a resolver seus problemas.<br>Models of decision-making need to reflect human psychology. Towards this end, this work is based on Sparse Distributed Memory (SDM), a psychologically and neuroscientifically plausible model of human memory, published by Pentti Kanerva in 1988. Kanerva‘s model of memory holds a critical point: prior to this point, a previously stored item can be easily retrieved; but beyond this point an item cannot be retrieved. Kanerva has methodically calculated this point for a particu- lar set of (fixed) parameters. Here we extend this knowledge, through computational simulations, in which we analyzed this critical point behavior under several scenarios: in several dimensions, in number of stored items in memory, and in number of times the item has been rehearsed. We also derive a function that, when minimized, determines the value of critical distance according to the state of the memory. A secondary goal is to present the SDM in a simple and intuitive way in order that researchers of other areas can think how SDM can help them to understand and solve their problems.
14
Wecke, Liliane. "Cardiac memory studies in two human models /." Stockholm, 2006. http://diss.kib.ki.se/2006/91-7140-614-X/.
Повний текст джерела
15
Bambeck, Timothy J. "A computer controlled data acquisition and control system for a shape-memory alloy artificial muscle." Ohio : Ohio University, 1993. http://www.ohiolink.edu/etd/view.cgi?ohiou1174935244.
Повний текст джерела
16
Narayanan, Pavanesh. "Sensor-less Control of Shape Memory Alloy Using Artificial Neural Network and Variable Structure Controller." University of Toledo / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1416501021.
Повний текст джерела
17
Stone, Erik E. Skubic Marge. "Adaptive temporal difference learning of spatial memory in the water maze task." Diss., Columbia, Mo. : University of Missouri--Columbia, 2009. http://hdl.handle.net/10355/6586.
Повний текст джерелаАнотація:
The entire thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file; a non-technical public abstract appears in the public.pdf file. Title from PDF of title page (University of Missouri--Columbia, viewed on January 22, 2010). Thesis advisor: Dr. Marjorie Skubic. Includes bibliographical references.
18
Helman, Shaun. "The knowledge and processing underlying the structural mere exposure effect." Thesis, University of Reading, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.314322.
Повний текст джерела
19
Tadesse, Yonas Tegegn. "Creating Human-Like Facial Expressions Utilizing Artificial Muscles and Skin." Diss., Virginia Tech, 2009. http://hdl.handle.net/10919/30159.
Повний текст джерелаАнотація:
Mimicking facial structures for a robotic head requires integration of multiple structural and mechanical parameters, design, synthesis and control of muscle actuation, architecture of the linkages between actuation points within skin, and implementation of the deformation matrix with respect to global skull coordinates. In this dissertation, humanoid faces were designed and fabricated to investigate all the parameters mentioned above. A prototype face and neck was developed using servo motors and extensively characterized. In this prototype, a neck mechanism was designed using a four bar mechanism to achieve nodding and turning motions. The modular neck prototype simplifies the assembly and statically in equilibrium and hence demands less torque from the cost-effective RC servo motor. The mechanism was critically investigated for dynamic performance and it was found out that RC servo based robotic head requires a PD external controller to overcome inherent overshoot. The servo based robotic head was analyzed for design and control of anchor, architecture of linkages between actuation points within skin, and deformation matrix with respect to global coordinate for creating specific expressions. A functional relationship between deformation vector of facial control points and actuator parameter, skin elasticity and angular position of actuator was derived. The developed analysis method is applicable to any rotary actuator technology utilized for facial expressions and takes into account the skin stiffness. The artificial skin materials for facial expression were synthesized using platinum-cured silicone elastomeric material (Reynolds Advanced Materials Inc.) with base consisting of mainly polyorganosiloxanes, amorphous silica and platinum-siloxane complex compounds. Systematic incorporation of porosity in this material was found to lower the force required to deform the skin in the axial direction.
The performance of the servo motor based face was quite realistic but it suffers from the drawback of large power consumption, bulky, heavy, and limited functionality. Thus, significant effort was made in developing a Biometal fiber and Flexinol shape memory alloy actuator (SMA) based biped mountable baby head facial structure which resembles the form and functionality of a human being. SMAs were embedded inside a skull and connected to elastomeric skin at control points. An engineered architecture of skull was fabricated that incorporates all the muscles with their 35 routine pulleys, two fire wire CMOS cameras that serve as eyes, and a battery powered microcontroller base driving circuit within the total dimensions of 140 mm x 90 mm x 110 mm. The driving circuit was designed such that it can be easily integrated with biped and processed in real-time. The humanoid face with 12DOF was mounted on the body of DARwIn (Dynamic Anthropomorphic Robot with Intelligence) robot which has 21 DOF resulting in a total of 33 DOF system. Characterization results on the face and associated design issues are described that provide pathways for developing human-like facial anatomy. Numerical simulation using Simulink was conducted to assess the performance of a prototypic robotic face mainly focusing on jaw movement. A graphical method “Graphical Facial Expression Analysis and Design (GFEAD)” was developed that can be used to allocate the sinking points on robotic head. The method assumes that the origin of the action units are known prior and the underlying criterion in the design of faces being deformation of a soft elastomeric skin through tension in anchoring wires attached on one end to the sinking point and on the other to the actuator. Experimental characterization on a prototyping humanoid face was performed to validate the model and demonstrate the applicability on a generic platform.
During characterization of the SMA based face, it was found that the currently available artificial muscle technologies do not meet the entire requirement for being embedded in the skin and provide the required strain rate, maximum strain, blocking force, response time and energy density. Thus an effort was made to develop conducting polymer based artificial muscles which can meet the metrics of human muscle. Composite stripe and zigzag actuators consisting of a sandwich structure polypyrrole /poly(vinylidene difluoride) (PPy/PVDF) were synthesized using potentiodynamic film growth on gold electrodes. The synthesis was done from an aqueous solution containing tetrabutylammonium Perchlorate (TBAP) and pyrrole by polymerization at room temperature. For depositing thin PPy films and thereby minimizing the response time, an experimental optimization of the deposition conditions was performed. The number of current-potential (potentiodynamic) growth cycles and the thickness of the deposited PPy film were highly correlated in the initial stages of polymer film growth. Strip actuator of size 11 x 5 mm2 with 63μM exhibited a deflection of 3mm under 1V DC voltage and 2mm deflection under 8V AC voltage at 0.5 Hz. It was found that three-segment zigzag actuator of segment length 15x2.5mm and thickness 63μM amplifies the displacement by 1.5 times.
A study was also conducted on the synthesis and characterization of thick and thin film polypyrrole (PPy) – metal composite actuators. The fabrication method consisted of three steps based upon the approach proposed by Ding et al.: (i) winding the conductive spiral structure around the platinum (Pt)-wire core, (ii) deposition of PPy film on the Pt-wire core, and (iii) removal of the Pt-wire core. This approach yielded good performance from the synthesized actuators, but was complex to implement due to the difficulty in implementing the third step. To overcome the problem of mechanical damage occurring during withdrawal of Pt-wire, the core was replaced with a dispensable gold coated polylactide fiber that could be dissolved at the end of deposition step. Experimental results indicate that thin film actuators perform better in terms of response time and blocking force. A unique muscle-like structure with smoothly varying cross-section was grown by combining layer by layer deposition with changes in position and orientation of the counter electrode in reference to the working electrode. Synthesis of polypyrrole–metal coil was conducted in aqueous solution containing 0.25 M Pyrrole, 0.10 M TBAP and 0.50 M KCl. The actuator consisted of a single layer of platinum winding on a core substrate. Electrochemical characterization for free strain and blocking stress was conducted 0.1 M TBAP solution and a 6% free strain was obtained at an applied potential of 6V DC after 80 s stimulation time. The blocking stress 18 kPa was estimated by extrapolating the strain magnitude on stress-strain diagram. For axial type actuator with coil winding, a generalized governing equation for the electrochemical stress generated from polypyrrole–metal coil which accommodates the effect of magnetic field due to winding was proposed and numerically studied. It was considered as insightful modeling.<br>Ph. D.
20
Hirtzlin, Tifenn. "Digital Implementation of Neuromorphic systems using Emerging Memory devices." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPAST071.
Повний текст джерелаАнотація:
Depuis les années soixante-dix l'évolution des performances des circuits électroniques repose exclusivement sur l'amélioration des performances des transistors. Ce composant a des propriétés extraordinaires puisque lorsque ses dimensions sont réduites, toutes ses caractéristiques sont améliorées. Mais, dû à certaines limites physiques fondamentales, la diminution des dimensions des transistors n’est plus possible. Néanmoins, de nouveaux nano-composants mémoire innovants qui peuvent être intégré conjointement avec les transistors voient le jour tant au niveau académique qu'industriel, ce qui constitue une opportunité pour repenser complètement l'architecture des circuits électroniques actuels. L'une des voies de recherche possible est l’inspiration du fonctionnement du cerveau biologique. Ce dernier peut accomplir des tâches complexes et variées en consommant très peu d’énergie. Ces travaux de thèse explorent trois paradigmes neuro-inspirés pour l'utilisation de ces composants mémoire. Chacune de ces approches explore différentes problématiques du calcul en mémoire<br>While electronics has prospered inexorably for several decades, its leading source of progress will stop in the next coming years, due to the fundamental technological limits of transistors. Nevertheless, microelectronics is currently offering a major breakthrough: in recent years, memory technologies have undergone incredible progress, opening the way for multiple research venues in embedded systems. Additionally, a major feature for future years will be the ability to integrate different technologies on the same chip. new emerging memory devices that can be embedded in the core of the CMOS, such as Resistive Random Access Memory (RRAM) or Spin Torque Magnetic Tunnel Junction (STMRAM) based on naturally intelligent inmemory-computing architecture. Three braininspired algorithms are carefully examined: Bayesian reasoning binarized neural networks, and an approach that further exploits the intrinsic behavior of components, population coding of neurons. Each of these approaches explores different aspects of in-memory computing
21
Ehrich, John Fitzgerald. "The effects of L1 orthography on processing an artificial logographic script." Thesis, Queensland University of Technology, 2008. https://eprints.qut.edu.au/35768/1/John_Fitzgerald_Ehrich_Thesis.pdf.
Повний текст джерелаАнотація:
To date, studies have focused on the acquisition of alphabetic second languages (L2s) in alphabetic first language (L1) users, demonstrating significant transfer effects. The present study examined the process from a reverse perspective, comparing logographic (Mandarin-Chinese) and alphabetic (English) L1 users in the acquisition of an artificial logographic script, in order to determine whether similar language-specific advantageous transfer effects occurred. English monolinguals, English-French bilinguals and Chinese-English bilinguals learned a small set of symbols in an artificial logographic script and were subsequently tested on their ability to process this script in regard to three main perspectives: L2 reading, L2 working memory (WM), and inner processing strategies. In terms of L2 reading, a lexical decision task on the artificial symbols revealed markedly faster response times in the Chinese-English bilinguals, indicating a logographic transfer effect suggestive of a visual processing advantage. A syntactic decision task evaluated the degree to which the new language was mastered beyond the single word level. No L1-specific transfer effects were found for artificial language strings. In order to investigate visual processing of the artificial logographs further, a series of WM experiments were conducted. Artificial logographs were recalled under concurrent auditory and visuo-spatial suppression conditions to disrupt phonological and visual processing, respectively. No L1-specific transfer effects were found, indicating no visual processing advantage of the Chinese-English bilinguals. However, a bilingual processing advantage was found indicative of a superior ability to control executive functions. In terms of L1 WM, the Chinese-English bilinguals outperformed the alphabetic L1 users when processing L1 words, indicating a language experience-specific advantage. Questionnaire data on the cognitive strategies that were deployed during the acquisition and processing of the artificial logographic script revealed that the Chinese-English bilinguals rated their inner speech as lower than the alphabetic L1 users, suggesting that they were transferring their phonological processing skill set to the acquisition and use of an artificial script. Overall, evidence was found to indicate that language learners transfer specific L1 orthographic processing skills to L2 logographic processing. Additionally, evidence was also found indicating that a bilingual history enhances cognitive performance in L2.
22
Kianzad, Soheil. "A treatise on highly twisted artificial muscle : thermally driven shape memory alloy yarn and coiled nylon actuators." Thesis, University of British Columbia, 2015. http://hdl.handle.net/2429/54782.
Повний текст джерелаАнотація:
A new perspective in the field of actuators was opened by the demonstration of multiwall carbon nanotube based actuators by Foroughi et al, in 2011. The approach involves applying a high degree of twist to create large torsional actuation in carbon nanotube yarns, and more recently in coiled nylon filaments. In this thesis torsional actuation is further studied in nylon, and extended to shape memory alloys (SMA).
Torsional actuation is demonstrated using 25 μm diameter micro strands of shape memory alloy (SMAs) that are twisted together. These form yarns with Young’s modulus of 13.5 GPa in the Martensitic phase and 18 GPa in the Austenite state. In torsion, the SMA yarns show more than 8,000 rpm peak rotational speed with 11 reversible rotations for an 8 cm long yarn. This is observed upon applying 0.47 W/cm electrical input power. Providing more than 5 N.m/kg torque, SMA yarns may be of interest in biomedical and other applications. The mechanical behaviour of coiled nylon actuators is studied by testing elastic modulus and by investigating tensile stroke as a function of temperature. Loads that range from 35 MPa to 155 MPa were applied. For the nylon and the coiling conditions used, active thermal contraction totals 19.5 % when the temperature is raised from -40 ⁰C to 160 ⁰C, with most contraction above the glass transition temperature. Introducing various cooling methods was shown to enable increased rate of actuation up to several Hertz. Nylon coiled actuators potentially provide affordable and viable solutions for driving mechanical devices as recently demonstrated in robotic hands and arms. A new biomimetic arrangement of the nylon actuator is presented that imitates the human pennate muscle in structure, including the ability to vary stiffness by a factor of 9 and to increase isometric force from 19 N to 37 N by recruiting additional fibers.<br>Applied Science, Faculty of<br>Electrical and Computer Engineering, Department of<br>Graduate
23
Holmes, Andrew J. "The use of non-volatile a-Si:H memory devices for synaptic weight storage in artificial neural networks." Thesis, University of Edinburgh, 1995. http://hdl.handle.net/1842/14085.
Повний текст джерелаАнотація:
This thesis describes the development of an ANN chip in which a-Si:H resistors are integrated with CMOS circuitry. This eliminates the need for external refresh or neuron circuitry required by ANN designs based on dynamic storage techniques. The a-Si:H memory technology was developed in collaboration with Dundee University and is in effect a programmable, non-volatile, semiconductor resistor. The device consists of a thin 1000A layer of a-Si:H sandwiched between vanadium and chromium electrodes. During the project a total of three test chips were designed and fabricated. The first chip was used to investigate the fabrication of memory devices on the surface of a CMOS wafer: previously all the test devices had been constructed on glass slides. Results from this chip showed that it was possible to fabricate programmable a-Si:H resistors on a CMOS chip. The second chip contained five different synapse designs all of which used the a-Si:H resistor as the memory element. The best of these was then used in the construction of the final ANN chip. This chip contained an 8 x 8 array of synapses and digital addressing, and required minimal support circuitry. Conclusions are drawn both about the performance of the a-Si:H memory device and the alternative approaches to non-volatile storage in ANN chips, and recommendations are made for future work in this area.
24
Reese, Caitlin S. "The Implicit Artificial Grammar Task: Preliminary Evaluation of its Potential for Detection of Noncredible Effort/Malingering." Ohio University / OhioLINK, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1406763394.
Повний текст джерела
25
Elvir, Miguel. "EPISODIC MEMORY MODEL FOR EMBODIED CONVERSATIONAL AGENTS." Master's thesis, University of Central Florida, 2010. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/3000.
Повний текст джерелаАнотація:
Embodied Conversational Agents (ECA) form part of a range of virtual characters whose intended purpose include engaging in natural conversations with human users. While works in literature are ripe with descriptions of attempts at producing viable ECA architectures, few authors have addressed the role of episodic memory models in conversational agents. This form of memory, which provides a sense of autobiographic record-keeping in humans, has only recently been peripherally integrated into dialog management tools for ECAs. In our work, we propose to take a closer look at the shared characteristics of episodic memory models in recent examples from the field. Additionally, we propose several enhancements to these existing models through a unified episodic memory model for ECAÂ s. As part of our research into episodic memory models, we present a process for determining the prevalent contexts in the conversations obtained from the aforementioned interactions. The process presented demonstrates the use of statistical and machine learning services, as well as Natural Language Processing techniques to extract relevant snippets from conversations. Finally, mechanisms to store, retrieve, and recall episodes from previous conversations are discussed. A primary contribution of this research is in the context of contemporary memory models for conversational agents and cognitive architectures. To the best of our knowledge, this is the first attempt at providing a comparative summary of existing works. As implementations of ECAs become more complex and encompass more realistic conversation engines, we expect that episodic memory models will continue to evolve and further enhance the naturalness of conversations.<br>M.S.Cp.E.<br>School of Electrical Engineering and Computer Science<br>Engineering and Computer Science<br>Computer Engineering MSCpE
26
Lindell, Adam. "Pulse Repetition Interval Time Series Modeling for Radar Waves using Long Short-Term Memory Artificial Recurrent Neural Networks." Thesis, Uppsala universitet, Avdelningen för beräkningsvetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-377865.
Повний текст джерелаАнотація:
This project is a performance study of Long Short-Term Memory artificial neural networks in the context of a specific time series prediction problem consisting of radar pulse trains. The network is tested both in terms of accuracy on a regular time series but also on an incomplete time series where values have been removed in order to test its robustness/resistance to small errors. The results indicate that the network can perform very well when no values are removed and can be trained relatively quickly using the parameters set in this project, although the robustness of the network seems to be quite low using this particular implementation.
27
Bhalala, Smita Ashesh 1966. "Modified Newton's method for supervised training of dynamical neural networks for applications in associative memory and nonlinear identification problems." Thesis, The University of Arizona, 1991. http://hdl.handle.net/10150/277969.
Повний текст джерелаАнотація:
There have been several innovative approaches towards realizing an intelligent architecture that utilizes artificial neural networks for applications in information processing. The development of supervised training rules for updating the adjustable parameters of neural networks has received extensive attention in the recent past. In this study, specific learning algorithms utilizing modified Newton's method for the optimization of the adjustable parameters of a dynamical neural network are developed. Computer simulation results show that the convergence performance of the proposed learning schemes match very closely that of the LMS learning algorithm for applications in the design of associative memories and nonlinear mapping problems. However, the implementation of the modified Newton's method is complex due to the computation of the slope of the nonlinear sigmoidal function, whereas, the LMS algorithm approximates the slope to be zero.
28
Longela, Makusudi Simon. "The development of an artificial hand using nickel-titanium as actuators." Thesis, Cape Peninsula University of Technology, 2013. http://hdl.handle.net/20.500.11838/2229.
Повний текст джерелаАнотація:
Thesis (MTech (Mechanical Engineering))--Cape Peninsula University of Technology, 2013.<br>This thesis outlines a proposed mechanical design, prototyping and testing of a five
fingered artificial hand made of 15 articulated joints actuated by Shape Memory
Alloys (SMAs) mimicking muscular functions. SMAs Artificial muscles were
incorporated in the forearm and artificial tendons made of nylon wires passing
through a hollow palm transmit the pulling force to bend the fingers. Torsion springs
set in each joint of the fingers create enough restoring force to straighten the finger
when the actuators are disengaged.
Nickel-Titanium (NiTi) wires were intrinsically embedded within the hand structure
allowing significant movements mimicking human hand-like gestures.
A control box made of switches connected to the artificial hand helps to control each
gesture.
A modular approach was taken in the design to facilitate the manufacture and
assembly processes. Nickel-Titanium wires were used as actuators to perform the
artificial muscle functions by changing their crystallographic structures due to Joule's
heating.
Rapid prototyping techniques were employed to manufacture the hand in ABS plastic.
29
Francis, Anthony G. Jr. "Context-sensitive asynchronous memory : a general experience-based method for managing information access in cognitive agents." Diss., Georgia Institute of Technology, 2000. http://hdl.handle.net/1853/9177.
Повний текст джерела
30
Bonnet, Djohan. "Synaptic uncertainty for in-memory computing." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPAST037.
Повний текст джерелаАнотація:
La forte demande pour les réseaux de neurones artificiels, combinée à leur coût énergétique élevé dû au "memory bottleneck" des architectures de von-Neumann, a intensifié les efforts pour surmonter les contraintes du matériel informatique. Cette thèse explore le domaine interdisciplinaire du calcul neuromorphique, en se concentrant sur des études expérimentales, des algorithmes et la conception de circuit intégrés. Dans la partie expérimentale, les caractéristiques électriques des mémoires vives basées sur la transition métal-oxyde (OxRAMs) et les mémoires à changement de phase (PCMs) sont étudiées pour comprendre leurs différentes variabilités. De plus, un réseau de neurones bayésien est implémenté sur 75 puces electroniques. Passant aux algorithmes, la recherche implique des analyses expérimentales et théoriques d'une nouvelle méthode d'apprentissage nommée MESU (MEtaplasticity from Synaptic Uncertainty). Cette méthode exploite l'incertitude synaptique dans les réseaux de neurones Bayésien pour l'apprentissage continuel. Enfin, pour la partie conception de circuit, un démonstrateur pour le calcul dans la mémoire est développé sans outils d'automatisation, tirant parti de la technologie OxRAM, couvrant des aspects allant du dimensionnement des transistors jusqu'à la réalisation du dessin des masques<br>The high demand for Artificial Neural Networks, combined with their high energy cost due to the memory bottleneck of von-Neumann architectures, has intensified efforts to overcome hardware constraints. This thesis explores the interdisciplinary field of neuromorphic computing, focusing on experimental studies, algorithms, and integrated circuit design. The experimental part investigates the electrical characteristics of resistive random access memories based on metal-oxide transition (OxRAMs) and phase change memories (PCMs) to understand their different variabilities. Additionally, a Bayesian neural network is implemented across 75 electronic chips. Moving to algorithms, the research involves both experimental and theoretical analyses of a novel learning method named MESU, which stands for metaplasticity from synaptic uncertainty. This method exploits synaptic uncertainty in Bayesian neural networks for continual learning. Lastly, for the circuit design part, a full custom in-memory computing demonstrator is developed, leveraging OxRAM technology, covering aspects from transistor sizing to layout realization
31
Bazzi, Hussein. "Resistive memory co-design in CMOS technologies." Electronic Thesis or Diss., Aix-Marseille, 2020. http://www.theses.fr/2020AIXM0567.
Повний текст джерелаАнотація:
De nombreuses applications (internet des objets, systèmes embarqués automobiles et médicales, intelligence artificielle) ont besoin d’un circuit intégré (ou SoC pour System on Chip) avec des mémoires non volatiles embarquées performantes pour fonctionner de manière optimale. Bien que la mémoire Flash soit largement utilisée aujourd'hui, cette technologie nécessite une tension élevée pour les opérations de programmation et présente des problèmes de fiabilité difficiles à gérer au-delà du nœud technologique 18 nm, augmentant les coûts de conception et de fabrication des circuits. Dans ce contexte, l'industrie du semi-conducteur est à la recherche d’une mémoire non volatile alternative pouvant remplacer les mémoires Flash. Parmi les candidats actuellement étudiés (MRAM - mémoire à accès aléatoire magnétique, PCM - mémoire à changement de phase, FeRAM - mémoire à accès aléatoire Ferroélectrique), les mémoires résistives (RRAM) offrent de meilleures performances sur différents points capitaux : compatibilité avec le processus de fabrication standard CMOS, consommation de courant, rapidité de fonctionnement, etc. La technologie RRAM peut être aisément introduite dans n'importe quel flot de conception ouvrant la voie au développement de nouvelles architectures qui répondent à l’engorgement des systèmes classiques Von Neumann. Dans cette thèse, l'objet principal est de montrer le potentiel d’intégration des dispositifs RRAM avec la technologie CMOS, à l’aide de simulation et de mesures électriques, afin d’élaborer différentes structures hybrides : mémoires à accès aléatoire statique (SRAM) non volatiles, générateurs de nombres aléatoires (TRNG) et réseaux de neurones artificiels<br>Many diversified applications (internet of things, embedded systems for automotive and medical applications, artificial intelligence) require an integrated circuit (SoC, System on Chip) with high-performance non-volatile memories to operate optimally. Although Flash memory is widely used today, this technology needs high voltage for programing operations and has reliability issues that are hard to handle beyond 18 nm technological node, increasing the cost of circuit design and fabrication. In this context, the semiconductor industry seeks an alternative non-volatile memory that can replace Flash memories. Among possible candidates (MRAM - Magnetic Random Access Memory, PCM - Phase Change Memory, FeRAM - Ferroelectric Random Access Memory), Resistive memories (RRAMs) offer superior performances on essential key points: compatibility with CMOS manufacturing processes, scalability, current consumption (standby and active), operational speed. Due to its relatively simple structure, RRAM technology can be easily integrated in any design flow opening the way for the development of new architectures that answer Von Neumann bottleneck. In this thesis, the main object is to show the integration abilities of RRAM devices with CMOS technology, using circuit design and electrical measurements, in order to develop different hybrid structures: non-volatile Static Random Access Memories (SRAM), True Random Number Generator (TRNG) and artificial neural networks
32
Forslund, John, and Jesper Fahlén. "Predicting customer purchase behavior within Telecom : How Artificial Intelligence can be collaborated into marketing efforts." Thesis, KTH, Skolan för industriell teknik och management (ITM), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-279575.
Повний текст джерелаАнотація:
This study aims to investigate the implementation of an AI model that predicts customer purchases, in the telecom industry. The thesis also outlines how such an AI model can assist decision-making in marketing strategies. It is concluded that designing the AI model by following a Recurrent Neural Network (RNN) architecture with a Long Short-Term Memory (LSTM) layer, allow for a successful implementation with satisfactory model performances. Stepwise instructions to construct such model is presented in the methodology section of the study. The RNN-LSTM model further serves as an assisting tool for marketers to assess how a consumer’s website behavior affect their purchase behavior over time, in a quantitative way - by observing what the authors refer to as the Customer Purchase Propensity Journey (CPPJ). The firm empirical basis of CPPJ, can help organizations improve their allocation of marketing resources, as well as benefit the organization’s online presence by allowing for personalization of the customer experience.<br>Denna studie undersöker implementeringen av en AI-modell som förutspår kunders köp, inom telekombranschen. Studien syftar även till att påvisa hur en sådan AI-modell kan understödja beslutsfattande i marknadsföringsstrategier. Genom att designa AI-modellen med en Recurrent Neural Network (RNN) arkitektur med ett Long Short-Term Memory (LSTM) lager, drar studien slutsatsen att en sådan design möjliggör en framgångsrik implementering med tillfredsställande modellprestation. Instruktioner erhålls stegvis för att konstruera modellen i studiens metodikavsnitt. RNN-LSTM-modellen kan med fördel användas som ett hjälpande verktyg till marknadsförare för att bedöma hur en kunds beteendemönster på en hemsida påverkar deras köpbeteende över tiden, på ett kvantitativt sätt - genom att observera det ramverk som författarna kallar för Kundköpbenägenhetsresan, på engelska Customer Purchase Propensity Journey (CPPJ). Den empiriska grunden av CPPJ kan hjälpa organisationer att förbättra allokeringen av marknadsföringsresurser, samt gynna deras digitala närvaro genom att möjliggöra mer relevant personalisering i kundupplevelsen.
33
Hellman, James. ""As Mind to the Body": Prudence and Artificial Memory in the Illustrations and Commentary of George Sandys' Ovid's Metamorphosis Englished (1632)." VCU Scholars Compass, 2013. http://scholarscompass.vcu.edu/etd/506.
Повний текст джерелаАнотація:
This thesis is an analysis of an English verse translation of Ovid's Metamorphoses, published in 1632 by the Englishman George Sandys. This book included a full English commentary and was illustrated by several full-plate engravings. This study examines the edition's elaborate utilization of the rhetorical practices of artificial memory and related concepts of rhetorical invention. It demonstrates that these rhetorical practices were chosen and implemented for their inherent structural appropriateness for the cultivation of prudence, or practical wisdom. It reveals that the lessons in practical wisdom encoded in the work through the techniques of artificial memory were particularly aimed at political issues and the concerns of rulers. From the work's preoccupation with prudence as appropriate for a ruler, and from the dedication and prefatory texts, it becomes clear that it was intended to provide a means of counsel, or advice, to the King Charles I in an elaborate poetic format.
34
Endo, Yoichiro. "Countering Murphys law the use of anticipation and improvisation via an episodic memory in support of intelligent robot behavior /." Diss., Atlanta, Ga. : Georgia Institute of Technology, 2008. http://hdl.handle.net/1853/26466.
Повний текст джерелаАнотація:
Thesis (Ph.D)--Computing, Georgia Institute of Technology, 2009.<br>Committee Chair: Arkin, Ronald; Committee Member: Balch, Tucker; Committee Member: Dellaert, Frank; Committee Member: Potter, Steve; Committee Member: Ram, Ashwin. Part of the SMARTech Electronic Thesis and Dissertation Collection.
35
Price, Ryan William. "Hierarchical Temporal Memory Cortical Learning Algorithm for Pattern Recognition on Multi-core Architectures." PDXScholar, 2011. https://pdxscholar.library.pdx.edu/open_access_etds/202.
Повний текст джерелаАнотація:
Strongly inspired by an understanding of mammalian cortical structure and function, the Hierarchical Temporal Memory Cortical Learning Algorithm (HTM CLA) is a promising new approach to problems of recognition and inference in space and time. Only a subset of the theoretical framework of this algorithm has been studied, but it is already clear that there is a need for more information about the performance of HTM CLA with real data and the associated computational costs. For the work presented here, a complete implementation of Numenta's current algorithm was done in C++. In validating the implementation, first and higher order sequence learning was briefly examined, as was algorithm behavior with noisy data doing simple pattern recognition. A pattern recognition task was created using sequences of handwritten digits and performance analysis of the sequential implementation was performed. The analysis indicates that the resulting rapid increase in computing load may impact algorithm scalability, which may, in turn, be an obstacle to widespread adoption of the algorithm. Two critical hotspots in the sequential code were identified and a parallelized version was developed using OpenMP multi-threading. Scalability analysis of the parallel implementation was performed on a state of the art multi-core computing platform. Modest speedup was readily achieved with straightforward parallelization. Parallelization on multi-core systems is an attractive choice for moderate sized applications, but significantly larger ones are likely to remain infeasible without more specialized hardware acceleration accompanied by optimizations to the algorithm.
36
Salihoglu, Utku. "Toward a brain-like memory with recurrent neural networks." Doctoral thesis, Universite Libre de Bruxelles, 2009. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/210221.
Повний текст джерелаАнотація:
For the last twenty years, several assumptions have been expressed in the fields of information processing, neurophysiology and cognitive sciences. First, neural networks and their dynamical behaviors in terms of attractors is the natural way adopted by the brain to encode information. Any information item to be stored in the neural network should be coded in some way or another in one of the dynamical attractors of the brain, and retrieved by stimulating the network to trap its dynamics in the desired item’s basin of attraction. The second view shared by neural network researchers is to base the learning of the synaptic matrix on a local Hebbian mechanism. The third assumption is the presence of chaos and the benefit gained by its presence. Chaos, although very simply produced, inherently possesses an infinite amount of cyclic regimes that can be exploited for coding information. Moreover, the network randomly wanders around these unstable regimes in a spontaneous way, thus rapidly proposing alternative responses to external stimuli, and being easily able to switch from one of these potential attractors to another in response to any incoming stimulus. Finally, since their introduction sixty years ago, cell assemblies have proved to be a powerful paradigm for brain information processing. After their introduction in artificial intelligence, cell assemblies became commonly used in computational neuroscience as a neural substrate for content addressable memories. <p> <p>Based on these assumptions, this thesis provides a computer model of neural network simulation of a brain-like memory. It first shows experimentally that the more information is to be stored in robust cyclic attractors, the more chaos appears as a regime in the background, erratically itinerating among brief appearances of these attractors. Chaos does not appear to be the cause, but the consequence of the learning. However, it appears as an helpful consequence that widens the network’s encoding capacity. To learn the information to be stored, two supervised iterative Hebbian learning algorithm are proposed. One leaves the semantics of the attractors to be associated with the feeding data unprescribed, while the other defines it a priori. Both algorithms show good results, even though the first one is more robust and has a greater storing capacity. Using these promising results, a biologically plausible alternative to these algorithms is proposed using cell assemblies as substrate for information. Even though this is not new, the mechanisms underlying their formation are poorly understood and, so far, there are no biologically plausible algorithms that can explain how external stimuli can be online stored in cell assemblies. This thesis provide such a solution combining a fast Hebbian/anti-Hebbian learning of the network's recurrent connections for the creation of new cell assemblies, and a slower feedback signal which stabilizes the cell assemblies by learning the feed forward input connections. This last mechanism is inspired by the retroaxonal hypothesis. <p><br>Doctorat en Sciences<br>info:eu-repo/semantics/nonPublished
37
Mustafa, Hassan M., and Ayoub Al-Hamadi. "On Teaching Quality Improvement of a Mathematical Topic Using Artificial Neural Networks Modeling (With a Case Study)." Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2012. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-80718.
Повний текст джерелаАнотація:
This paper inspired by simulation by Artificial Neural Networks (ANNs) applied recently for evaluation of phonics methodology to teach children "how to read". A novel approach for teaching a mathematical topic using a computer aided learning (CAL) package applied at educational field (a children classroom). Interesting practical results obtained after field application of suggested CAL package with and without associated teacher's voice. Presented study highly recommends application of a novel teaching trend based on behaviorism and individuals' learning styles. That is to improve
quality of children mathematical learning performance.
38
Jüngel, Matthias. "The memory-based paradigm for vision-based robot localization." Doctoral thesis, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, 2012. http://dx.doi.org/10.18452/16593.
Повний текст джерелаАнотація:
Für mobile autonome Roboter ist ein solides Modell der Umwelt eine wichtige Voraussetzung um die richtigen Entscheidungen zu treffen. Die gängigen existierenden Verfahren zur Weltmodellierung basieren auf dem Bayes-Filter und verarbeiten Informationen mit Hidden Markov Modellen. Dabei wird der geschätzte Zustand der Welt (Belief) iterativ aktualisiert, indem abwechselnd Sensordaten und das Wissen über die ausgeführten Aktionen des Roboters integriert werden; alle Informationen aus der Vergangenheit sind im Belief integriert. Wenn Sensordaten nur einen geringen Informationsgehalt haben, wie zum Beispiel Peilungsmessungen, kommen sowohl parametrische Filter (z.B. Kalman-Filter) als auch nicht-parametrische Filter (z.B. Partikel-Filter) schnell an ihre Grenzen. Das Problem ist dabei die Repräsentation des Beliefs. Es kann zum Beispiel sein, dass die gaußschen Modelle beim Kalman-Filter nicht ausreichen oder Partikel-Filter so viele Partikel benötigen, dass die Rechendauer zu groß wird. In dieser Dissertation stelle ich ein neues Verfahren zur Weltmodellierung vor, das Informationen nicht sofort integriert, sondern erst bei Bedarf kombiniert. Das Verfahren wird exemplarisch auf verschiedene Anwendungsfälle aus dem RoboCup (autonome Roboter spielen Fußball) angewendet. Es wird gezeigt, wie vierbeinige und humanoide Roboter ihre Position und Ausrichtung auf einem Spielfeld sehr präzise bestimmen können. Grundlage für die Lokalisierung sind bildbasierte Peilungsmessungen zu Objekten. Für die Roboter-Ausrichtung sind dabei Feldlinien eine wichtige Informationsquelle. In dieser Dissertation wird ein Verfahren zur Erkennung von Feldlinien in Kamerabildern vorgestellt, das ohne Kalibrierung auskommt und sehr gute Resultate liefert, auch wenn es starke Schatten und Verdeckungen im Bild gibt.<br>For autonomous mobile robots, a solid world model is an important prerequisite for decision making. Current state estimation techniques are based on Hidden Markov Models and Bayesian filtering. These methods estimate the state of the world (belief) in an iterative manner. Data obtained from perceptions and actions is accumulated in the belief which can be represented parametrically (like in Kalman filters) or non-parametrically (like in particle filters). When the sensor''s information gain is low, as in the case of bearing-only measurements, the representation of the belief can be challenging. For instance, a Kalman filter''s Gaussian models might not be sufficient or a particle filter might need an unreasonable number of particles. In this thesis, I introduce a new state estimation method which doesn''t accumulate information in a belief. Instead, perceptions and actions are stored in a memory. Based on this, the state is calculated when needed. The system has a particular advantage when processing sparse information. This thesis presents how the memory-based technique can be applied to examples from RoboCup (autonomous robots play soccer). In experiments, it is shown how four-legged and humanoid robots can localize themselves very precisely on a soccer field. The localization is based on bearings to objects obtained from digital images. This thesis presents a new technique to recognize field lines which doesn''t need any pre-run calibration and also works when the field lines are partly concealed and affected by shadows.
39
Musunuru, Venkata Krishna Kanth. "Virtuo-ITS: An Interactive Tutoring System to Teach Virtual Memory Concepts of an Operating System." Wright State University / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=wright1495481049986755.
Повний текст джерела
40
Neto, Camilo Rodrigues. "Propriedades de recuperação de memória em redes neurais atratoras." Universidade de São Paulo, 1997. http://www.teses.usp.br/teses/disponiveis/76/76131/tde-31102008-173551/.
Повний текст джерелаАнотація:
Redes neurais atratoras são redes de neurônios artificiais com realimentacão e sem estrutura de conexão pré-definida. Estes tipos de redes apresentam uma rica dinâmica dissipativa e são freqüentemente utilizadas como memórias associativas. Tais dispositivos tem a propriedade de recuperar uma memória previamente armazenada, mesmo quando expostos a informação parcial ou degradada daquela memória. Armazenar uma memória significa criar um atrator para ela na dinâmica da rede e isto e feito especificando-se adequadamente os pesos sinápticos. Nesta tese, nos concentramos basicamente em duas maneiras de se definir os pesos sinapticos, que dão origem ao modelo da pseudo-inversa e ao modelo dos pesos ótimos. Para redes neurais extremamente diluídas, onde a conectividade C e o número de neurônios N satisfazem à condição C« In N obtivemos os diagramas de fase no espaço completo de parâmetros dos modelos da pseudo-inversa e dos pesos ótimos através da analise da dinâmica da correlação de recuperação dos padrões armazenados. Alem disso, investigamos as propriedades de recuperação de redes neurais completamente conectadas através de duas abordagens: a investigação analítica da vizinhança dos padrões armazenados e a enumeração exaustiva dos atratores por meio de simulações numéricas. Finalmente. estudamos analiticamente o problema da categorizarão no modelo da pseudo-inversa. A categorizar;ao em redes neurais atratoras e a capacidade da rede treinada com exemplos de um conceito desenvolver um atrator para este conceito.<br>Attractor neural networks are feedback neural networks with no pre-defined connection structure. These types of neural networks present a rich dissipative dynamics and, in general, are used as associative memory devices. Such devices have the capacity to retrieve a previously stored memory, even when exposed to partial or degraded information. To store a memory means to create an attractor for it in the network dynamics, and this is done by specifying the set of synaptic weighs. In this thesis, we concentrate on two classical ways of specifying the synaptics weighs: the pseudo-inverse and the optimal weighs models. For extremely diluted neural networks, for which the connectivity C and the number of neurons N satisfy the condition C « In N, we obtain the phase diagrams in the complete space of the model parameters through the analytical study of the retrieval overlap dynamics. We also investigate the retrieval properties of fully connected neural networks using two approaches: the analytical study of the neighborhood of the stored patterns, and the exhaustive enumeration of the attractors via numerical simulations. Finally, we study analytically the problem of categorization in the pseudo-inverse model. Categorization in attractor neural networks is the capacity to create an attractor for a concept to which the network has had access only through a finite number of examples.
41
Samikwa, Eric. "Flood Prediction System Using IoT and Artificial Neural Networks with Edge Computing." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-280299.
Повний текст джерелаАнотація:
Flood disasters affect millions of people across the world by causing severe loss of life and colossal damage to property. Internet of things (IoT) has been applied in areas such as flood prediction, flood monitoring, flood detection, etc. Although IoT technologies cannot stop the occurrence of flood disasters, they are exceptionally valuable apparatus for conveyance of catastrophe readiness and counteractive action data. Advances have been made in flood prediction using artificial neural networks (ANN). Despite the various advancements in flood prediction systems through the use of ANN, there has been less focus on the utilisation of edge computing for improved efficiency and reliability of such systems. In this thesis, a system for short-term flood prediction that uses IoT and ANN, where the prediction computation is carried out on a low power edge device is proposed. The system monitors real-time rainfall and water level sensor data and predicts ahead of time flood water levels using long short-term memory. The system can be deployed on battery power as it uses low power IoT devices and communication technology. The results of evaluating a prototype of the system indicate a good performance in terms of flood prediction accuracy and response time. The application of ANN with edge computing will help improve the efficiency of real-time flood early warning systems by bringing the prediction computation close to where data is collected.<br>Översvämningar drabbar miljontals människor över hela världen genom att orsaka dödsfall och förstöra egendom. Sakernas Internet (IoT) har använts i områden som översvämnings förutsägelse, översvämnings övervakning, översvämning upptäckt, etc. Även om IoT-teknologier inte kan stoppa förekomsten av översvämningar, så är de mycket användbara när det kommer till transport av katastrofberedskap och motverkande handlingsdata. Utveckling har skett när det kommer till att förutspå översvämningar med hjälp av artificiella neuronnät (ANN). Trots de olika framstegen inom system för att förutspå översvämningar genom ANN, så har det varit mindre fokus på användningen av edge computing vilket skulle kunna förbättra effektivitet och tillförlitlighet. I detta examensarbete föreslås ett system för kortsiktig översvämningsförutsägelse genom IoT och ANN, där gissningsberäkningen utförs över en låg effekt edge enhet. Systemet övervakar sensordata från regn och vattennivå i realtid och förutspår översvämningsvattennivåer i förtid genom att använda långt korttidsminne. Systemet kan köras på batteri eftersom det använder låg effekt IoT-enheter och kommunikationsteknik. Resultaten från en utvärdering av en prototyp av systemet indikerar en bra prestanda när det kommer till noggrannhet att förutspå översvämningar och responstid. Användningen av ANN med edge computing kommer att förbättra effektiviteten av tidiga varningssystem för översvämningar i realtid genom att ta gissningsberäkningen närmare till där datan samlas.
42
Comiran, Mariane. "Toxidez por cobre: reflexos na qualidade de sementes e no desenvolvimento inicial de aveia preta." Universidade Federal de Santa Maria, 2017. http://repositorio.ufsm.br/handle/1/11623.
Повний текст джерелаАнотація:
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES<br>in the soill elevated over the years through anthropogenic actions such as the application of
manure and cupping fungicides. As a reflection of these increases the establishment and
development of plants grown in these environments can be limited and
compromised. Considering the particularities of the different species in resisting and
completing their cycle on these conditions this work aimed to evaluate Cu interference on the
establishment and initial growth of black oats. The treatments were set up in 5x2 bifactorial,
with five concentrations of copper (0, 60, 120, 180, 240 μM) and two sub lots (vigor
levels). Thus, analyzes of physiological parameters of black oat seedlings and plants from two
sub lots, one artificially aged and another not, both originated from a single lot, were performed.
Two experiments were carried out; in the first one, physiological parameters were evaluated
which comprise the establishment capacity of the seedlings such as the first count and
germination test in B.O.D germinator with controlled conditions; the second one consisted in
hydroponic plant cultivation and evaluated physiological parameters of growth, such as length
and dry mass of shoot and root, and length and total dry mass. A completely randomized design
was adopted in both experiments, being the second one in a split-split plot arrangement. Cu
concentrations did not affect seedling establishment capacity, on the other hand the vigor of the
seed sub lot affected this ability, with more vigorous (not aged) seeds sub lot having a better
establishment. Cu concentrations were detrimental to the initial growth of black oat plants
above 60 μM independent of sub lot studied. Seedlings from the non-aged sub lot (high vigor)
presented higher initial growth than those from the aged sub lot (low vigor), however
acclimatization in the hydroponic system equaled them in root growth and caused an inversion
in the total plant growth, being this higher in low vigor sub lot plants.<br>O cobre (Cu) está entre os metais cujos teores em solo foram elevados ao longo dos anos em
decorrência de ações antrópicas como a aplicação de dejetos de animas e fungicidas cúpricos.
Como reflexo destes aumentos o estabelecimento e o desenvolvimento das plantas cultivadas
nestes ambientes pode ser limitado e comprometido. Consideradas as particularidades das
diferentes espécies em resistirem e completarem seu ciclo sobre estas condições pretendeu-se
com este trabalho avaliar a interferência do Cu sobre o estabelecimento e crescimento inicial
da aveia preta. Os tratamentos foram configurados em bifatorial 5x2, com cinco concentrações
de cobre (0, 60, 120, 180, 240 μM) e dois sublotes (níveis de vigor). Nesse sentido, foram
realizadas análises dos parâmetros fisiológicos de plântulas e plantas de aveia preta de dois
sublotes de sementes, um envelhecido e outro não envelhecido, ambos originados de um único
lote. Foram realizados dois experimentos; o primeiro, avaliou parâmetros fisiológicos que
compreendem a capacidade de estabelecimento das plântulas, através dos testes de primeira
contagem e germinação de sementes em germinador tipo BOD com condições controladas; o
segundo experimento, consistiu do cultivo de plantas em sistema hidropônico e avaliou
parâmetros fisiológicos de crescimento, como o comprimento e a massa seca de parte aérea e
raiz, e comprimento e massa seca total. Foi adotado delineamento inteiramente casualizado em
ambos os experimentos, sendo o segundo experimento com arranjo experimental em parcela
sub subdividida. As concentrações de Cu não afetaram a capacidade de estabelecimento de
plântulas, por outro lado o vigor do sublote de sementes afetou esta capacidade, sendo que
melhor estabelecimento foi observado no sublote não envelhecido (alto vigor). O crescimento
inicial de plantas de aveia preta foi influenciado negativamente por concentrações de Cu
superiores a 60 μM independente do sublote em estudo. Plântulas oriundas do sublote não
envelhecido (alto vigor) apresentaram crescimento inicial superior as oriundas do sublote
envelhecido (baixo vigor), entretanto a aclimatação em sistema hidropônico as igualou em
crescimento de raiz e ocasionou uma inversão no crescimento total da planta, sendo este
superior em plantas do sublote de baixo vigor.
43
Vaughan, Renata Aparecida da Rocha. "Avaliação das funções executivas em portadores de fibrilação atrial e insuficiência cardíaca." Universidade de São Paulo, 2017. http://www.teses.usp.br/teses/disponiveis/5/5142/tde-30012018-105412/.
Повний текст джерелаАнотація:
Introdução: A Insuficiência Cardíaca (IC) e a Fibrilação Atrial (FA) são patologias frequentes na população idosa e estão associadas a alterações da esfera cognitiva. No entanto, suas consequências sobre as funções executivas, responsáveis pela resolução de problemas, ainda não estão totalmente esclarecidas. Objetivo: investigar as características do funcionamento executivo em pacientes com FA e/ou IC e identificar se tal funcionamento é equiparável ao de um grupo controle. Método: Estudo observacional, de coorte transversal, realizado em hospital de atenção terciária em cardiologia que avaliou 191 sujeitos, com uma média de 69,1 anos de idade (mín.: 60; Max.: 82) distribuídos em cinco grupos distintos: com FA, com IC associada à FA, com IC e controles (com e sem marca-passo artificial MP). Os grupos foram pareados por faixa etária e variáveis sócio-demográficas, submetidos à avaliação neuropsicológica e a análise estatística envolveu testes não paramétricos (Kruskall-Wallys e Mann-Whitney), qui-quadrado de Pearson e teste exato de Fisher. Resultados: Nos indivíduos com FA comparados aos controles sem MP, observamos diferenças estatisticamente significativas relacionadas a memória operacional (p = 0,034), a memória tardia (p = 0,015), a memória semântica e fluência verbal (p < 0,001), a compreensão (p < 0,001), ao planejamento e a habilidade visuoespacial (p < 0,001), a percepção visual e a linguagem (p< 0,001) e ao controle inibitório e a velocidade de processamento, nas três fases do instrumento (p < 0,008; p < 0,004; p < 0,002). Já nos indivíduos com FA associada à IC, as diferenças observadas envolveram: a memória semântica e a fluência verbal (p = 0,05), o planejamento e a habilidade visuoespacial (p < 0,001), a percepção visual e a linguagem (p < 0,001) e o controle inibitório e a velocidade de processamento (p = 0,002; p < 0,001; p = 0,145, respectivamente). Os sujeitos com IC demonstraram o mesmo desempenho do grupo de indivíduos com FA e IC, com diferenças relacionadas às mesmas funções, exceto na primeira fase do instrumento que avaliou controle inibitório e a velocidade de processamento (p < 0,001). Quanto à funcionalidade, não observamos diferença estatisticamente significativa entre os grupos. Conclusões: O funcionamento executivo de indivíduos com FA ou IC não é equiparável ao de indivíduos sem essas doenças. A FA, de uma perspectiva neuropsicológica, intensifica o prejuízo das FE e também da memória<br>Introduction: Heart Failure (HF) and Atrial Fibrillation (AF) are frequent pathologies in the elderly population and are associated with cognitive disorders. However, its consequences on executive functions, which are responsible for solving problems, have not yet been fully clarified. Objective: to investigate the characteristics of executive functioning in patients with AF and/or HF and to identify if such functioning is comparable to that of a control group. Methods: A cross-sectional observational study performed in a tertiary care hospital in cardiology, which evaluated 191 subjects with a mean age of 69.1 years (min.: 60, Max.: 82) distributed in five different groups: AF, with HF associated with AF, with HF and controls (with and without pacemaker). The groups were matched by age group and socio-demographic variables, submitted to neuropsychological evaluation and statistical analysis involved non-parametric tests (Kruskall-Wallys and Mann-Whitney), Pearson\'s chi-square and Fisher\'s exact test. Results: In subjects with AF compared to non-pacemaker controls, we observed statistically significant differences related to operational memory (p = 0.034), late memory (p = 0.015), semantic memory and verbal fluency (p < 0.001), comprehension P < 0.001), visuospatial planning and ability (p < 0.001), visual perception and language (p < 0.001) and inhibitory control and processing speed in the three phases of the instrument (p < 0.008; p < 0.004, p < 0.002). In subjects with HF associated with HF, the observed differences involved: semantic memory and verbal fluency (p = 0.05), planning and visuospatial ability (p < 0.001), visual perception and language (p < 0.001) and inhibitory control and processing speed (p = 0.002, p < 0.001, p = 0.145, respectively). Subjects with HF demonstrated the same performance of the group of individuals with AF and HF, with differences related to the same functions, except in the first phase of the instrument that evaluated inhibitory control and processing speed (p < 0.001). Regarding functionality, we did not observe a statistically significant difference between groups. Conclusions: The executive functioning of individuals with AF or IC is not comparable to that of individuals without these diseases. AF, from a neuropsychological perspective, intensifies the damage of FE and memory
44
Pacheco, Renato Ferrari. "Módulos neurais para modelagem de falsas memórias." Universidade de São Paulo, 2004. http://www.teses.usp.br/teses/disponiveis/18/18133/tde-12052017-103355/.
Повний текст джерелаАнотація:
As falsas memórias são um tipo falha de memória, em que o indivíduo pode (a) reconhecer como tendo visto antes um objeto ou evento que não tenha ocorrido ou (b) não reconhecer algo previamente presenciado. Estes são o falso reconhecimento e a rejeição errada. Segundo a teoria do rastro difuso, dois processos distintos agem em paralelo durante a memorização e reconhecimento, um sobre as informações literais (verbatim) e o outro sobre a essência do significado da palavra (gist). Neste trabalho é proposto um sistema modular de redes neurais artificiais que considera estes dois processos, características funcionais das estruturas cerebrais envolvidas na memorização e fluxo de informação análogo ao ocorrido no cérebro. O modelo neural é validado através de treinamento para armazenar e recuperar listas de palavras semanticamente relacionadas. Na formulação do modelo e da representação foram considerados a representação fonológica e significado das palavras, de forma a simular as computações ocorridas e os resultados obtidos em experimentos efetuados com sujeitos humanos. Nestes experimentos, 12 listas de aproximadamente 15 palavras, cada lista semanticamente relacionadas a um tema são ouvidas e, em seguida, algumas destas palavras, a palavra tema e outras palavras não relacionadas são também ouvidas e os indivíduos respondem se cada palavra fora ouvida previamente. Os resultados obtidos computacionalmente aproximam-se bastante dos resultados obtidos com sujeitos humanos, e o modelo produzido serve como base para estudo das influências dos diversos processos atuantes durante a memorização e reconhecimento.<br>False memories are a kind of memory failure, in which the subject may (a) recognize as known an never seen object or never happened fact or (b) don\'t recognize something that was already presented him. These are false memories and wrong rejections. According to false memory theory, two parallel processes act during memorization and recognition, one on verbatim information and other on gist information. In this work is proposed a artificial neural network model system that takes in account these two processes, functional issues about brain structures involved on memorization and the an information flow analog to the occurred in the brain. The neural model is validated by training to store in recover lists of semantically related words. In the model and representation scheme formulation, phonological and semantic informations were used intending to simulate brain computations and results of human subjects experiments. In such experiment, 12 lists of something about 15 semantically related words, are heard and, in the second step, in the sequence, many of these words, other related words and not related words are heard in a recognition test, when subjets say if that word was or was not heard during memorization steps. Results obtained from computer tests are very close of human results, and the produced model may be used as a tool for analysis of the influences of the many processes that take place during memorization and recognition.
45
Huang, Yiming. "Phoneme Recognition Using Neural Network and Sequence Learning Model." Ohio University / OhioLINK, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1236027180.
Повний текст джерела
46
Abrishami, Hedayat. "Deep Learning Based Electrocardiogram Delineation." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563525992210273.
Повний текст джерела
47
Figuerola, Wilfredo Blanco. "Din?mica da Plasticidade Sin?ptica em neur?nios do hipocampo durante ciclos de sono: um estudo computacional." Universidade Federal do Rio Grande do Norte, 2012. http://repositorio.ufrn.br:8080/jspui/handle/123456789/15187.
Повний текст джерелаАнотація:
Made available in DSpace on 2014-12-17T14:55:05Z (GMT). No. of bitstreams: 1
WilfredoBF_TESE.pdf: 4144764 bytes, checksum: ae0670814eb6793d7e5af7d0973a9f65 (MD5)
Previous issue date: 2012-03-26<br>Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior<br>Several research lines show that sleep favors memory consolidation and learning. It has been proposed that the cognitive role of sleep is derived from a global scaling of
synaptic weights, able to homeostatically restore the ability to learn new things, erasing memories overnight. This phenomenon is typical of slow-wave sleep (SWS) and characterized
by non-Hebbian mechanisms, i.e., mechanisms independent of synchronous neuronal activity. Another view holds that sleep also triggers the specific enhancement of synaptic connections, carrying out the embossing of certain mnemonic traces within
a lattice of synaptic weights rescaled each night. Such an embossing is understood as the combination of Hebbian and non-Hebbian mechanisms, capable of increasing and decreasing
respectively the synaptic weights in complementary circuits, leading to selective memory improvement and a restructuring of synaptic configuration (SC) that can be crucial for the generation of new behaviors ( insights ). The empirical findings indicate that initiation of Hebbian plasticity during sleep occurs in the transition of the SWS to the stage of rapid eye movement (REM), possibly due to the significant differences between
the firing rates regimes of the stages and the up-regulation of factors involved in longterm synaptic plasticity. In this study the theories of homeostasis and embossing were compared using an artificial neural network (ANN) fed with action potentials recorded in the hippocampus of rats during the sleep-wake cycle. In the simulation in which the ANN did not apply the long-term plasticity mechanisms during sleep (SWS-transition REM), the synaptic weights distribution was re-scaled inexorably, for its mean value proportional to the input firing rate, erasing the synaptic weights pattern that had been established
initially. In contrast, when the long-term plasticity is modeled during the transition SWSREM, an increase of synaptic weights were observed in the range of initial/low values, redistributing effectively the weights in a way to reinforce a subset of synapses over time. The results suggest that a positive regulation coming from the long-term plasticity can
completely change the role of sleep: its absence leads to forgetting; its presence leads to a positive mnemonic change<br>Diversas linhas de pesquisa demonstram que o sono favorece a consolida??o de mem?rias e o aprendizado. Tem sido proposto que o papel cognitivo do sono deriva de um redimensionamento global dos pesos sin?pticos, capaz de restabelecer homeostaticamente a capacidade de aprender coisas novas, apagando mem?rias durante a noite. Tal fen?meno seria t?pico do sono de ondas lentas ( slow wave sleep , SWS) e caracterizado
por mecanismos n?o-Hebbianos, isto ?, independentes da atividade neuronal sincr?nica. Outra abordagem postula que o sono desencadeia tamb?m um realce de conex?es sin?pticas
espec?ficas, levando a um entalhamento de certos tra?os mnem?nicos no ?mbito de uma matriz de pesos sin?pticos redimensionados a cada noite. Tal entalhamento ?
entendido como a combina??o de mecanismos Hebbianos e n?o-Hebbianos, capazes respectivamente de aumentar e diminuir os pesos sin?pticos em circuitos complementares,
levando ? melhoria seletiva de mem?rias e a uma reestrutura??o da configura??o sin?ptica ( synaptic configuration , SC) que pode ser crucial para a gera??o de novos comportamentos
( insights ). Os achados emp?ricos indicam que a indu??o de plasticidade Hebbiana durante o sono acontece na transi??o do SWS para o est?gio de movimento r?pido dos olhos ( rapid eye movement , REM), possivelmente devido ?s grandes diferen?as entre os regimes das taxas de disparos entre os estados e ? regula??o positiva de fatores envolvidos na plasticidade sin?ptica de longo prazo. Neste estudo, as teorias da homeostase
e do entalhamento foram comparadas usando uma rede neural artificial ( artificial neural network , ANN) alimentada com potenciais de a??o registrados no hipocampo de ratos
durante todo o ciclo sono-vig?lia. Na simula??o em que a ANN n?o aplicou mecanismos de plasticidade de longo prazo durante o sono (transi??o SWS-REM), a distribui??o pesos sin?pticos foram inexoravelmente re-escalada para uma media proporcional ? taxa de disparo das entradas, apagando eventualmente o padr?o de pesos sin?pticos inicialmente estabelecido. Em contraste, quando a plasticidade de longo prazo foi modelada durante a
transi??o SWS-REM, o aumento dos pesos sin?pticos foi observado em toda a gama de valores iniciais, efetivamente redistribuindo os pesos de modo a refor?ar um subconjunto
de sinapses ao longo do tempo. Os resultados sugerem que uma regula??o positiva proveniente da plasticidade de longo prazo pode alterar completamente o papel do sono: sua
aus?ncia leva ao esquecimento, sua presen?a leva a uma mudan?a mnem?nica positiva
48
Elwér, Åsa. "Learning by Liking- a Mere Exposure Version of the AGL Paradigm." Thesis, Linköping University, Department of Computer and Information Science, 2004. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-2075.
Повний текст джерелаАнотація:
<p>The artificial grammar learning (AGL) paradigm has been intensively researched since the 60-s. In general, these investigations attempt to study the implicit acquisition of structural regularities. Among other things, it has been suggested that the AGL paradigm can serve as a model for the process of acquiring a natural language. Thus it can serve as a well-controlled laboratory task that might be used to understand certain aspects of the process of language acquisition. For example the AGL paradigm has been used in an attempt to isolate the acquisition of syntactic aspects of language. Several experimental studies show that the participants acquire knowledge of the underlying rule system since they are able to differentiate grammatical strings from non-grammatical ones. It has been argued that the traditionally conducted AGL paradigm with grammaticality instructions might make the task explicit, at least during the test phase. In order to imitate the language learning process as close as possible, to rule out the possibility of an explicit component during the testing phase (i.e., keeping the retrieval process implicit) and to rule out explicit rule conformity or rule following, we modified the classical AGL paradigm. In a behavioural study we combined the AGL paradigm with an altered mere exposure paradigm in an attempt to better model aspects of language acquisition. We were able to show that subjects, classifying under mere exposure instructions, categorize grammatical and non-grammatical strings just as well as those solving the classification task with the grammaticality instructions. This indicates that the mere exposure version might serve as a more appropriate model for language acquisition.</p>
49
Lawrie, Sofía. "Information representation and processing in neuronal networks: from biological to artificial systems and from first to second-order statistics." Doctoral thesis, Universitat Pompeu Fabra, 2022. http://hdl.handle.net/10803/673989.
Повний текст джерелаАнотація:
Neuronal networks are today hypothesized to the basis for the computing capabilities of biological nervous systems. In the same manner, artificial neuronal systems are intensively exploited for a diversity of industrial and scientific applications. However, how information is represented and processed by these networks remains under debate, meaning that it is not clear which sets of neuronal activity features are useful for computation. In this thesis, I present a set of results that link the first-order statistics of neuronal activity with behavior, in the general context of encoding/decoding to analyse experimental data collected while non human primates performed a working memory task. Subsequently, I go beyond the first-order and show that the second-order statistics of neuronal activity in reservoir computing, a recurrent artificial network model, make up a robust candidate for information representation and transmission for the classification of multivariate inputs.<br>Las redes neuronales se presentan hoy, hipotéticamente, como las responsables de las capacidades computacionales de los sistemas nerviosos biológicos. De la misma manera, los sistemas neuronales artificiales son intensamente explotados en una diversidad de aplicaciones industriales y científicas. No obstante, cómo la información es representada y procesada por estas redes está aún sujeto a debate. Es decir, no está claro qué propiedades de la actividad neuronal son útiles para llevar a cabo computaciones. En esta tesis, presento un conjunto de resultados que relaciona el primer orden estadístico de la actividad neuronal con comportamiento, en el contexto general de codificación/decodificación, para analizar datos recolectados mientras primates no humanos realizaban una tarea de memoria de trabajo. Subsecuentemente, voy más allá del primer orden y muestro que las estadísticas de segundo orden en computación de reservorios, un modelo de red neuronal artificial y recurrente, constituyen un candidato robusto para la representación y transmisión de información con el fin de clasificar señales multidimensionales.
50
Freire, Ananda Lima. "A DimensÃo temporal no projeto de classificadores de padrÃes para navegaÃÃo de robÃs mÃveis: um estudo de caso." Universidade Federal do CearÃ, 2009. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=16223.
Повний текст джерелаАнотація:
CoordenaÃÃo de AperfeÃoamento de Pessoal de NÃvel Superior<br>Este trabalho investiga o grau de influÃncia que a inclusÃo de mecanismos de memÃria de curta duraÃÃo (MCD) exercem sobre o desempenho de classificadores neurais quando aplicados em tarefas de navegaÃÃo de robÃs. Em particular, trata da navegaÃÃo do tipo Wall Following. Para este fim, quatro conhecidas arquiteturas neurais (Perceptron LogÃstico, Perceptron Multicamadas, Mistura de Especialistas e rede de Elman) sÃo usadas com o intuito de associar
diferentes padrÃes de leituras sensoriais com quatro classes de aÃÃes prÃ-determinadas. Todas as etapas dos experimentos - aquisiÃÃo dos dados, seleÃÃo e treinamento das arquiteturas em simulador, alÃm da execuÃÃo das mesmas em robà mÃvel real (SCITOS G5) - sÃo escritas em detalhes. Os resultados obtidos sugerem que a tarefa de seguir paredes, formulada como um problema de classificaÃÃo de padrÃes, à nÃo-linearmente separÃvel, resultado este que favorece a rede MLP quando os classificadores sÃo treinados sem MCD. Contudo, se mecanismos de MCD sÃo usados, entÃo atà mesmo uma rede linear à capaz de executar a tarefa de interesse com sucesso<br>This work reports results of an investigation on the degree of influence that the inclusion
of short-term memory mechanisms has on the performance of neural classifiers when applied
to robot navigation tasks. In particular, we deal with the well-known strategy of navigating by
âwall-followingâ. For this purpose, four neural architectures (Logistic Perceptron, Multilayer
Perceptron, Mixture of Experts and Elman network) are used to associate different sensory
input patterns with four predetermined action categories. All stages of the experiments - data
acquisition, selection and training of the architectures in a simulator and their execution on a
real mobile robot - are described. The obtained results suggest that the wall-following task,
formulated as a pattern classification problem, is nonlinearly separable, a result that favors the
MLP network if no memory of input patterns are taken into account. If short-term memory
mechanisms are used, then even a linear network is able to perform the same task successfully