Dissertations / Theses on the topic 'Neural-symbolic'
To see the other types of publications on this topic, follow the link: Neural-symbolic.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 29 dissertations / theses for your research on the topic 'Neural-symbolic.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Bader, Sebastian. "Neural-Symbolic Integration." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2009. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-25468.
Full textAbstract:
In this thesis, we discuss different techniques to bridge the gap between two different approaches to artificial intelligence: the symbolic and the connectionist paradigm. Both approaches have quite contrasting advantages and disadvantages. Research in the area of neural-symbolic integration aims at bridging the gap between them.
Starting from a human readable logic program, we construct connectionist systems, which behave equivalently. Afterwards, those systems can be trained, and later the refined knowledge be extracted.
2
Townsend, Joseph Paul. "Artificial development of neural-symbolic networks." Thesis, University of Exeter, 2014. http://hdl.handle.net/10871/15162.
Full textAbstract:
Artificial neural networks (ANNs) and logic programs have both been suggested as means of modelling human cognition. While ANNs are adaptable and relatively noise resistant, the information they represent is distributed across various neurons and is therefore difficult to interpret. On the contrary, symbolic systems such as logic programs are interpretable but less adaptable. Human cognition is performed in a network of biological neurons and yet is capable of representing symbols, and therefore an ideal model would combine the strengths of the two approaches. This is the goal of Neural-Symbolic Integration [4, 16, 21, 40], in which ANNs are used to produce interpretable, adaptable representations of logic programs and other symbolic models. One neural-symbolic model of reasoning is SHRUTI [89, 95], argued to exhibit biological plausibility in that it captures some aspects of real biological processes. SHRUTI's original developers also suggest that further biological plausibility can be ascribed to the fact that SHRUTI networks can be represented by a model of genetic development [96, 120]. The aims of this thesis are to support the claims of SHRUTI's developers by producing the first such genetic representation for SHRUTI networks and to explore biological plausibility further by investigating the evolvability of the proposed SHRUTI genome. The SHRUTI genome is developed and evolved using principles from Generative and Developmental Systems and Artificial Development [13, 105], in which genomes use indirect encoding to provide a set of instructions for the gradual development of the phenotype just as DNA does for biological organisms. This thesis presents genomes that develop SHRUTI representations of logical relations and episodic facts so that they are able to correctly answer questions on the knowledge they represent. The evolvability of the SHRUTI genomes is limited in that an evolutionary search was able to discover genomes for simple relational structures that did not include conjunction, but could not discover structures that enabled conjunctive relations or episodic facts to be learned. Experiments were performed to understand the SHRUTI fitness landscape and demonstrated that this landscape is unsuitable for navigation using an evolutionary search. Complex SHRUTI structures require that necessary substructures must be discovered in unison and not individually in order to yield a positive change in objective fitness that informs the evolutionary search of their discovery. The requirement for multiple substructures to be in place before fitness can be improved is probably owed to the localist representation of concepts and relations in SHRUTI. Therefore this thesis concludes by making a case for switching to more distributed representations as a possible means of improving evolvability in the future.
3
Xiao, Chunyang. "Neural-Symbolic Learning for Semantic Parsing." Thesis, Université de Lorraine, 2017. http://www.theses.fr/2017LORR0268/document.
Full textAbstract:
Notre but dans cette thèse est de construire un système qui réponde à une question en langue naturelle (NL) en représentant sa sémantique comme une forme logique (LF) et ensuite en calculant une réponse en exécutant cette LF sur une base de connaissances. La partie centrale d'un tel système est l'analyseur sémantique qui transforme les questions en formes logiques. Notre objectif est de construire des analyseurs sémantiques performants en apprenant à partir de paires (NL, LF). Nous proposons de combiner des réseaux neuronaux récurrents (RNN) avec des connaissances préalables symboliques exprimées à travers des grammaires hors-contexte (CFGs) et des automates. En intégrant des CFGs contrôlant la validité des LFs dans les processus d'apprentissage et d'inférence des RNNs, nous garantissons que les formes logiques générées sont bien formées; en intégrant, par le biais d'automates pondérés, des connaissances préalables sur la présence de certaines entités dans la LF, nous améliorons encore la performance de nos modèles. Expérimentalement, nous montrons que notre approche permet d'obtenir de meilleures performances que les analyseurs sémantiques qui n'utilisent pas de réseaux neuronaux, ainsi que les analyseurs à base de RNNs qui ne sont pas informés par de telles connaissances préalablesOur goal in this thesis is to build a system that answers a natural language question (NL) by representing its semantics as a logical form (LF) and then computing the answer by executing the LF over a knowledge base. The core part of such a system is the semantic parser that maps questions to logical forms. Our focus is how to build high-performance semantic parsers by learning from (NL, LF) pairs. We propose to combine recurrent neural networks (RNNs) with symbolic prior knowledge expressed through context-free grammars (CFGs) and automata. By integrating CFGs over LFs into the RNN training and inference processes, we guarantee that the generated logical forms are well-formed; by integrating, through weighted automata, prior knowledge over the presence of certain entities in the LF, we further enhance the performance of our models. Experimentally, we show that our approach achieves better performance than previous semantic parsers not using neural networks as well as RNNs not informed by such prior knowledge
4
Mann, Jordyn(Jordyn L. ). "Neural Bayesian goal inference for symbolic planning domains." Thesis, Massachusetts Institute of Technology, 2021. https://hdl.handle.net/1721.1/130701.
Full textAbstract:
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, February, 2021Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 51-52).
There are several reasons for which one may aim to infer the short- and long-term goals of agents in diverse physical domains. As increasingly powerful autonomous systems come into development, it is conceivable that they may eventually need to accurately infer the goals of humans. There are also more immediate reasons for which this sort of inference may be desirable, such as in the use case of intelligent personal assistants. This thesis introduces a neural Bayesian approach to goal inference in multiple symbolic planning domains and compares the results of this approach to the results of a recently developed Monte Carlo Bayesian inference method known as Sequential Inverse Plan Search (SIPS). SIPS is based on sequential Monte Carlo inference for Bayesian inversion of probabilistic plan search in Planning Domain Definition Language (PDDL) domains. In addition to the neural architectures, the thesis also introduces approaches for converting PDDL predicate state representations to numerical arrays and vectors suitable for input to the neural networks. The experimental results presented indicate that for the domains investigated, in cases where the training set is representative of the test set, the neural approach provides similar accuracy results to SIPS in the later portions of the observation sequences with a far shorter amortized time cost. However, in earlier timesteps of those observation sequences and in cases where the training set is less similar to the testing set, SIPS outperforms the neural approach in terms of accuracy. These results indicate that a model-based inference method where SIPS uses a neural proposal based on the neural networks designed in this thesis could have the potential to combine the advantages of both goal inference approaches by improving the speed of SIPS inference while maintaining generalizability and high accuracy throughout the timesteps of the observation sequences.
by Jordyn Mann.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
5
Noda, Itsuki. "Neural Networks that Learn Symbolic and Structred Representation of Information." Kyoto University, 1995. http://hdl.handle.net/2433/154663.
Full textAbstract:
本文データは平成22年度国立国会図書館の学位論文(博士)のデジタル化実施により作成された画像ファイルを基にpdf変換したものであるKyoto University (京都大学)
0048
新制・課程博士
博士(工学)
甲第5860号
工博第1404号
新制||工||978(附属図書館)
UT51-95-B205
京都大学大学院工学研究科電気工学専攻
(主査)教授 長尾 真, 教授 池田 克夫, 教授 矢島 脩三
学位規則第4条第1項該当
6
Chichlowski, Kazimierz O. "Modelling and recognition of continuous and symbolic data using artificial neural networks." Thesis, University of East Anglia, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.320829.
Full text
7
Chen, Hsinchun, P. Buntin, Linlin She, S. Sutjahjo, C. Sommer, and D. Neely. "Expert Prediction, Symbolic Learning, and Neural Networks: An Experiment on Greyhound Racing." IEEE, 1994. http://hdl.handle.net/10150/105472.
Full textAbstract:
Artificial Intelligence Lab, Department of MIS, University of ArizonaFor our research, we investigated a different problem-solving scenario called game playing, which is unstructured, complex, and seldom-studied. We considered several real-life game-playing scenarios and decided on greyhound racing. The large amount of historical information involved in the search poses a challenge for both human experts and machine-learning algorithms. The questions then become: Can machine-learning techniques reduce the uncertainty in a complex game-playing scenario? Can these methods outperform human experts in prediction? Our research sought to answer these questions.
8
Chen, Hsinchun. "Machine Learning for Information Retrieval: Neural Networks, Symbolic Learning, and Genetic Algorithms." Wiley Periodicals, Inc, 1995. http://hdl.handle.net/10150/106427.
Full textAbstract:
Artificial Intelligence Lab, Department of MIS, University of ArizonaInformation retrieval using probabilistic techniques has attracted significant attention on the part of researchers in information and computer science over the past few decades. In the 1980s, knowledge-based techniques also made an impressive contribution to “intelligent” information retrieval and indexing. More recently, information science researchers have turned to other newer artificial-intelligence- based inductive learning techniques including neural networks, symbolic learning, and genetic algorithms. These newer techniques, which are grounded on diverse paradigms, have provided great opportunities for researchers to enhance the information processing and retrieval capabilities of current information storage and retrieval systems. In this article, we first provide an overview of these newer techniques and their use in information science research. To familiarize readers with these techniques, we present three popular methods: the connectionist Hopfield network; the symbolic ID3/ID5R; and evolution- based genetic algorithms. We discuss their knowledge representations and algorithms in the context of information retrieval. Sample implementation and testing results from our own research are also provided for each technique. We believe these techniques are promising in their ability to analyze user queries, identify users’ information needs, and suggest alternatives for search. With proper user-system interactions, these methods can greatly complement the prevailing full-text, keywordbased, probabilistic, and knowledge-based techniques.
9
Tang, Zibin. "A new design approach for numeric-to-symbolic conversion using neural networks." PDXScholar, 1991. https://pdxscholar.library.pdx.edu/open_access_etds/4242.
Full textAbstract:
A new approach is proposed which uses a combination of a Backprop paradigm neural network along with some perceptron processing elements performing logic operations to construct a numeric-to-symbolic converter. The design approach proposed herein is capable of implementing a decision region defined by a multi-dimensional, non-linear boundary surface. By defining a "two-valued" subspace of the boundary surface, a Backprop paradigm neural network is used to model the boundary surf ace. An input vector is tested by the neural network boundary model (along with perceptron logic gates) to determine whether the incoming vector point is within the decision region or not. Experiments with two qualitatively different kinds of nonlinear surface were carried out to test and demonstrate the design approach.
10
Carmantini, Giovanni Sirio. "Dynamical systems theory for transparent symbolic computation in neuronal networks." Thesis, University of Plymouth, 2017. http://hdl.handle.net/10026.1/8647.
Full textAbstract:
In this thesis, we explore the interface between symbolic and dynamical system computation, with particular regard to dynamical system models of neuronal networks. In doing so, we adhere to a definition of computation as the physical realization of a formal system, where we say that a dynamical system performs a computation if a correspondence can be found between its dynamics on a vectorial space and the formal system’s dynamics on a symbolic space. Guided by this definition, we characterize computation in a range of neuronal network models. We first present a constructive mapping between a range of formal systems and Recurrent Neural Networks (RNNs), through the introduction of a Versatile Shift and a modular network architecture supporting its real-time simulation. We then move on to more detailed models of neural dynamics, characterizing the computation performed by networks of delay-pulse-coupled oscillators supporting the emergence of heteroclinic dynamics. We show that a correspondence can be found between these networks and Finite-State Transducers, and use the derived abstraction to investigate how noise affects computation in this class of systems, unveiling a surprising facilitatory effect on information transmission. Finally, we present a new dynamical framework for computation in neuronal networks based on the slow-fast dynamics paradigm, and discuss the consequences of our results for future work, specifically for what concerns the fields of interactive computation and Artificial Intelligence.
11
Borges, Rafael. "A neural-symbolic system for temporal reasoning with application to model verification and learning." Thesis, City University London, 2012. http://openaccess.city.ac.uk/1303/.
Full textAbstract:
The effective integration of knowledge representation, reasoning and learning into a robust computational model is one of the key challenges in Computer Science and Artificial Intelligence. In particular, temporal models have been fundamental in describing the behaviour of Computational and Neural-Symbolic Systems. Furthermore, knowledge acquisition of correct descriptions of the desired system’s behaviour is a complex task in several domains. Several efforts have been directed towards the development of tools that are capable of learning, describing and evolving software models. This thesis contributes to two major areas of Computer Science, namely Artificial Intelligence (AI) and Software Engineering. Under an AI perspective, we present a novel neural-symbolic computational model capable of representing and learning temporal knowledge in recurrent networks. The model works in integrated fashion. It enables the effective representation of temporal knowledge, the adaptation of temporal models to a set of desirable system properties and effective learning from examples, which in turn can lead to symbolic temporal knowledge extraction from the corresponding trained neural networks. The model is sound, from a theoretical standpoint, but is also tested in a number of case studies. An extension to the framework is shown to tackle aspects of verification and adaptation under the SE perspective. As regards verification, we make use of established techniques for model checking, which allow the verification of properties described as temporal models and return counter-examples whenever the properties are not satisfied. Our neural-symbolic framework is then extended to deal with different sources of information. This includes the translation of model descriptions into the neural structure, the evolution of such descriptions by the application of learning of counter examples, and also the learning of new models from simple observation of their behaviour. In summary, we believe the thesis describes a principled methodology for temporal knowledge representation, learning and extraction, shedding new light on predictive temporal models, not only from a theoretical standpoint, but also with respect to a potentially large number of applications in AI, Neural Computation and Software Engineering, where temporal knowledge plays a fundamental role.
12
Pollack, Courtney. "More Than Just Symbols: Mental and Neural Representations Related to Symbolic Number Processing in Mathematics." Thesis, Harvard University, 2016. http://nrs.harvard.edu/urn-3:HUL.InstRepos:27112714.
Full textAbstract:
The ability for students to understand numbers and other mathematical symbols is a crucial part of success in mathematics. Accordingly, it is important for researchers to understand the nature of symbolic number processing – the connections between a symbol or collection of symbols that convey numerical information (e.g., Arabic digits, arithmetic facts, literal symbols) and their related mental and neural representations. Research that joins the mind and brain sciences with education, such as educational neuroscience work, provides a powerful way to examine students’ symbolic number processing. Much of the research in this area has focused on processing of Arabic numerals in adults and children, with relatively less work on symbols common in intermediate and higher-level mathematics. This dissertation contributes two studies that focus on number processing for symbols beyond those used in basic numeracy, arithmetic facts and literal symbols.
The first study uses neuroimaging meta-analysis to examine whether there are brain regions that support both arithmetic and phonological processing. Results suggest that activity in frontal and temporo-occipital brain regions support both types of processing, and that there is recruitment of left temporoparietal areas for each type of processing, but these areas are regionally differentiated. The second study investigates the connection between literal symbols and their mental representations of quantity. Results suggest that there is a cognitive processing cost associated with connecting literal symbols to numerical referents because literal symbols have extant mental referents related to literacy.
Taken together, these studies expand the scope of existing research in educational neuroscience related to mathematics learning, to more fully incorporate notions of symbolic processing in intermediate and higher-level mathematics, and contribute to theory building on the connections between symbols in mathematics and their mental and neural representations. These studies also form the basis of my future work in educational neuroscience related to symbolic number processing, which will build and expand on the studies presented herein. Research on symbolic number processing that spans symbols learned in early numeracy (i.e., Arabic numerals) and in intermediate and higher-level mathematics (e.g., arithmetic facts, literal symbols) can facilitate a more complete picture of student learning, thereby supporting students’ mathematical development from early numeracy through advanced mathematics.
13
Cheng, Xiaoyu. "Applications of Artificial Neural Networks (ANNs) in exploring materials property-property correlations." Thesis, Queen Mary, University of London, 2014. http://qmro.qmul.ac.uk/xmlui/handle/123456789/7968.
Full textAbstract:
The discoveries of materials property-property correlations usually require prior knowledge or serendipity, the process of which can be time-consuming, costly, and labour-intensive. On the other hand, artificial neural networks (ANNs) are intelligent and scalable modelling techniques that have been used extensively to predict properties from materials’ composition or processing parameters, but are seldom used in exploring materials property-property correlations. The work presented in this thesis has employed ANNs combinatorial searches to explore the correlations of different materials properties, through which, ‘known’ correlations are verified, and ‘unknown’ correlations are revealed. An evaluation criterion is proposed and demonstrated to be useful in identifying nontrivial correlations. The work has also extended the application of ANNs in the fields of data corrections, property predictions and identifications of variables’ contributions. A systematic ANN protocol has been developed and tested against the known correlating equations of elastic properties and the experimental data, and is found to be reliable and effective to correct suspect data in a complicated situation where no prior knowledge exists. Moreover, the hardness increments of pure metals due to HPT are accurately predicted from shear modulus, melting temperature and Burgers vector. The first two variables are identified to have the largest impacts on hardening. Finally, a combined ANN-SR (symbolic regression) method is proposed to yield parsimonious correlating equations by ruling out redundant variables through the partial derivatives method and the connection weight approach, which are based on the analysis of the ANNs weight vectors. By applying this method, two simple equations that are at least as accurate as other models in providing a rapid estimation of the enthalpies of vaporization for compounds are obtained.
14
Borges, Rafael Vergara. "Investigações sobre raciocínio e aprendizagem temporal em modelos conexionistas." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2007. http://hdl.handle.net/10183/11488.
Full textAbstract:
A inteligência computacional é considerada por diferentes autores da atualidade como o destino manifesto da Ciência da Computação. A modelagem de diversos aspectos da cognição, tais como aprendizagem e raciocínio, tem sido a motivação para o desenvolvimento dos paradigmas simbólico e conexionista da inteligência artificial e, mais recentemente, para a integração de ambos com o intuito de unificar as vantagens de cada abordagem em um modelo único. Para o desenvolvimento de sistemas inteligentes, bem como para diversas outras áreas da Ciência da Computação, o tempo é considerado como um componente essencial, e a integração de uma dimensão temporal nestes sistemas é fundamental para conseguir uma representação melhor do comportamento cognitivo. Neste trabalho, propomos o SCTL (Sequential Connectionist Temporal Logic), uma abordagem neuro-simbólica para integrar conhecimento temporal, representado na forma de programas em lógica, em redes neurais recorrentes, de forma que a caracterização semântica de ambas representações sejam equivalentes. Além da estratégia para realizar esta conversão entre representações, e da verificação formal da equivalência semântica, também realizamos uma comparação da estratégia proposta com relação a outros sistemas que realizam representação simbólica e temporal em redes neurais. Por outro lado, também descrevemos, de foma algorítmica, o comportamento desejado para as redes neurais geradas, para realizar tanto inferência quanto aprendizagem sob uma ótica temporal. Este comportamento é analisado em diversos experimentos, buscando comprovar o desempenho de nossa abordagem para a modelagem cognitiva considerando diferentes condições e aplicações.Computational Intelligence is considered, by di erent authors in present days, the manifest destiny of Computer Science. The modelling of di erent aspects of cognition, such as learning and reasoning, has been a motivation for the integrated development of the symbolic and connectionist paradigms of artificial intelligence. More recently, such integration has led to the construction of models catering for integrated learning and reasoning. The integration of a temporal dimension into such systems is a relevant task as it allows for a richer representation of cognitive behaviour features, since time is considered an essential component in intelligent systems development. This work introduces SCTL (Sequential Connectionist Temporal Logic), a neuralsymbolic approach for integrating temporal knowledge, represented as logic programs, into recurrent neural networks. This integration is done in such a way that the semantic characterization of both representations are equivalent. Besides the strategy to achieve translation from one representation to another, and verification of the semantic equivalence, we also compare the proposed approach to other systems that perform symbolic and temporal representation in neural networks. Moreover, we describe the intended behaviour of the generated neural networks, for both temporal inference and learning through an algorithmic approach. Such behaviour is then evaluated by means several experiments, in order to analyse the performance of the model in cognitive modelling under di erent conditions and applications.
15
Kaithi, Bhargavacharan Reddy. "Knowledge Graph Reasoning over Unseen RDF Data." Wright State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=wright1571955816559707.
Full text
16
Galassi, Andrea. "Symbolic versus sub-symbolic approaches: a case study on training Deep Networks to play Nine Men’s Morris game." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/12859/.
Full textAbstract:
Le reti neurali artificiali, grazie alle nuove tecniche di Deep Learning, hanno completamente rivoluzionato il panorama tecnologico degli ultimi anni, dimostrandosi efficaci in svariati compiti di Intelligenza Artificiale e ambiti affini. Sarebbe quindi interessante analizzare in che modo e in quale misura le deep network possano sostituire le IA simboliche. Dopo gli impressionanti risultati ottenuti nel gioco del Go, come caso di studio è stato scelto il gioco del Mulino, un gioco da tavolo largamente diffuso e ampiamente studiato. È stato quindi creato il sistema completamente sub-simbolico Neural Nine Men’s Morris, che sfrutta tre reti neurali per scegliere la mossa migliore. Le reti sono state addestrate su un dataset di più di 1.500.000 coppie (stato del gioco, mossa migliore), creato in base alle scelte di una IA simbolica. Il sistema ha dimostrato di aver imparato le regole del gioco proponendo una mossa valida in più del 99% dei casi di test. Inoltre ha raggiunto un’accuratezza del 39% rispetto al dataset e ha sviluppato una propria strategia di gioco diversa da quella della IA addestratrice, dimostrandosi un giocatore peggiore o migliore a seconda dell’avversario. I risultati ottenuti in questo caso di studio mostrano che, in questo contesto, la chiave del successo nella progettazione di sistemi AI allo stato dell’arte sembra essere un buon bilanciamento tra tecniche simboliche e sub-simboliche, dando più rilevanza a queste ultime, con lo scopo di raggiungere la perfetta integrazione di queste tecnologie.
17
Lindberg, Maja. "The innate ability to cope with mathematics : A comparative fMRI study of children's and adults' neural activity during non-symbolic mathematical tasks." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-158199.
Full textAbstract:
Humans as well as animals are born with a number sense, an innate ability to make approximations (Dehaene, 1997). However, low numeracy is an issue today and have a larger impact on the individuals lives than poor reading abilities (Parsons & Bynner, 2006). To be able to understand the cause of developmental dyscalculia the fully functional brain coping with numbers must be further investigated. The aim of this study is hence to examine how the number sense develop during maturation. Seven children and seven adults (all healthy) have participated in this neuro imaging study. The participants were required to perform a non-symbolic mathematic task and a control task both outside and within the scanner. The results indicate a transition of active areas in the brain during maturation. In the children prefrontal areas were recruited, and for the adults the activation was primarily found in the parietal cortex. These findings, despite low statistical power indicates a shift of neural activity from a more cognitive demanding task into an automated task. Further studies will have to replicate the experiment to validate the findings of this study.
18
Kissner, Michael [Verfasser], Helmut [Akademischer Betreuer] Mayer, Helmut [Gutachter] Mayer, and Martin [Gutachter] Werner. "A Neural-Symbolic Framework for Mental Simulation / Michael Kissner ; Gutachter: Helmut Mayer, Martin Werner ; Akademischer Betreuer: Helmut Mayer ; Universität der Bundeswehr München, Fakultät für Informatik." Neubiberg : Universitätsbibliothek der Universität der Bundeswehr München, 2020. http://d-nb.info/1223995933/34.
Full text
19
Blanc, Jean-luc. "Transmission de l'information et complexité des activités de populations neuronales." Thesis, Aix-Marseille, 2012. http://www.theses.fr/2012AIXM4720/document.
Full textAbstract:
Dans cette thèse, nous abordons les problèmes de la transmission et du traitement de l'information par les assemblées de neurones, du point de vue de l'approche inter-disciplinaire des systèmes complexes en nous référant principalement aux formalismes de la théorie de l'information et de la théorie des systèmes dynamiques. Dans ce contexte, nous nous focalisons sur les mécanismes de représentation de l'information sensorielle par les activités neuronales à travers le codage neuronal. Nous explorons la structure de ce code, à plusieurs échelles grâce à l'étude de différents signaux électrophysiologiques issus de populations de neurones (signaux unitaires, LFP et EEG). Sur le plan méthodologique, nous avons implémenté différents indices permettant d'extraire objectivement l'information des activités neuronales, mais également d'en caractériser la dynamique sous-jacente à partir de séries temporelles de taille finie (le taux d'entropie). Nous avons également étudié un indicateur peu utilisé (le taux d'information mutuelle), qui permet de quantifier l'auto-organisation et les relations de couplage entre deux systèmes. Grâce à des approches théoriques et numériques, nous analysons les propriétés caractéristiques de ces indices et proposons leur utilisation dans le cadre de l'étude des systèmes neuronaux. Ce travail permet de caractériser la complexité de différentes activités neuronales associées aux dynamiques de transmission de l'informationIn this thesis, we address the problem of transmission and information processing by neuronal assemblies, in terms of the interdisciplinary approach of complex systems by referring mainly to the formalisms of information theory and dynamical systems. In this context, we focus on the mechanisms underlying sensory information representation by neuronal activity through neural coding. We explore the structure of this code under several scales through the study of different neuronal population electrophysiological signals (singel unit, LFP and EEG). We have implemented various indices in order to extract objectively information from neural activity, but also to characterize the underlying dynamics from finite size time series (the entropy rate). We also defined a new indicator (the mutual information rate), which quantifies self-organization and relations of coupling between two systems. Using theoretical and numerical approaches, we analyze some characteristic properties of these indices and propose their use in the context of the study of neural systems. This work allows us to characterize the complexity of different neuronal activity associated to information transmission dynamics
20
Mundy, Darren Paul. "Using a symbolic algorithm to extract rules from connectionist networks." Thesis, University of Exeter, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.240400.
Full text
21
Milaré, Claudia Regina. ""Extração de conhecimento de redes neurais artificiais utilizando sistemas de aprendizado simbólico e algoritmos genéticos"." Universidade de São Paulo, 2003. http://www.teses.usp.br/teses/disponiveis/55/55134/tde-11082004-004358/.
Full textAbstract:
Em Aprendizado de Máquina - AM não existe um único algoritmo que é sempre melhor para todos os domínios de aplicação. Na prática, diversas pesquisas mostram que Redes Neurais Artificiais - RNAs têm um 'bias' indutivo apropriado para diversos domínios. Em razão disso, RNAs têm sido aplicadas na resolução de vários problemas com desempenho satisfatório. Sistemas de AM simbólico possuem um 'bias' indutivo menos flexível do que as RNAs. Enquanto que as RNAs são capazes de aprender qualquer função, sistemas de AM simbólico geralmente aprendem conceitos que podem ser descritos na forma de hiperplanos. Por outro lado, sistemas de AM simbólico representam o conceito induzido por meio de estruturas simbólicas, as quais são geralmente compreensíveis pelos seres humanos. Assim, sistemas de AM simbólico são preferíveis quando é essencial a compreensibilidade do conceito induzido. RNAs carecem da capacidade de explicar suas decisões, uma vez que o conhecimento é codificado na forma de valores de seus pesos e 'thresholds'. Essa codificação é difícil de ser interpretada por seres humanos. Em diversos domínios de aplicação, tal como aprovação de crédito e diagnóstico médico, prover uma explicação sobre a classificação dada a um determinado caso é de crucial importância. De um modo similar, diversos usuários de sistemas de AM simbólico desejam validar o conhecimento induzido, com o objetivo de assegurar que a generalização feita pelo algoritmo é correta. Para que RNAs sejam aplicadas em um maior número de domínios, diversos pesquisadores têm proposto métodos para extrair conhecimento compreensível de RNAs. As principais contribuições desta tese são dois métodos que extraem conhecimento simbólico de RNAs. Os métodos propostos possuem diversas vantagens sobre outros métodos propostos previamente, tal como ser aplicáveis a qualquer arquitetura ou algoritmo de aprendizado de RNAs supervisionadas. O primeiro método proposto utiliza sistemas de AM simbólico para extrair conhecimento de RNAs, e o segundo método proposto estende o primeiro, combinado o conhecimento induzido por diversos sistemas de AM simbólico por meio de um Algoritmo Genético - AG. Os métodos propostos são analisados experimentalmente em diversos domínios de aplicação. Ambos os métodos são capazes de extrair conhecimento simbólico com alta fidelidade em relação à RNA treinada. Os métodos propostos são comparados com o método TREPAN, apresentando resultados promissores. TREPAN é um método bastante conhecido para extrair conhecimento de RNAs.In Machine Learning - ML there is not a single algorithm that is the best for all application domains. In practice, several research works have shown that Artificial Neural Networks - ANNs have an appropriate inductive bias for several domains. Thus, ANNs have been applied to a number of data sets with high predictive accuracy. Symbolic ML algorithms have a less flexible inductive bias than ANNs. While ANNs can learn any input-output mapping, i.e., ANNs have the universal approximation property, symbolic ML algorithms frequently learn concepts describing them using hyperplanes. On the other hand, symbolic algorithms are needed when a good understating of the decision process is essential, since symbolic ML algorithms express the knowledge induced using symbolic structures that can be interpreted and understood by humans. ANNs lack the capability of explaining their decisions since the knowledge is encoded as real-valued weights and biases of the network. This encoding is difficult to be interpreted by humans. In several application domains, such as credit approval and medical diagnosis, providing an explanation related to the classification given to a certain case is of crucial importance. In a similar way, several users of ML algorithms desire to validate the knowledge induced, in order to assure that the generalization made by the algorithm is correct. In order to apply ANNs to a larger number of application domains, several researches have proposed methods to extract comprehensible knowledge from ANNs. The primary contribution of this thesis consists of two methods that extract symbolic knowledge, expressed as decision rules, from ANNs. The proposed methods have several advantages over previous methods, such as being applicable to any architecture and supervised learning algorithm of ANNs. The first method uses standard symbolic ML algorithm to extract knowledge from ANNs, and the second method extends the first method by combining the knowledge induced by several symbolic ML algorithms through the application of a Genetic Algorithm - GA. The proposed methods are experimentally analyzed in a number of application domains. Results show that both methods are capable to extract symbolic knowledge having high fidelity with trained ANNs. The proposed methods are compared with TREPAN, showing promising results. TREPAN is a well known method to extract knowledge from ANNs.
22
Corchado, RodriÌguez Juan Manuel. "Neuro-symbolic model for real-time forecasting problems." Thesis, University of the West of Scotland, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.323760.
Full text
23
Bernardo, Alexandre. "Features for the Classification and Clustering of Music in Symbolic Format." Master's thesis, Department of Informatics, University of Lisbon, 2008. http://hdl.handle.net/10451/13947.
Full textAbstract:
Music Information Retrieval is, nowadays, a highly active branch of research and development in the computer science field, and focuses several topics, including music genre classification. The work presented in this paper focus on Track and Genre Classification of music stored using MIDI format, To address the problem of MIDI track classification, we extract a set of descriptors that are used to train a classifier implemented by a Neural Network, based on the pitch levels and durations that describe each track. Tracks are classified into four classes: Melody, Harmony, Bass and Drums. In order to characterize the musical content from each track, a vector of numeric descriptors, normally known as shallow structure description, is extracted. Then they are used as inputs for the classifier which was implemented in the Matlab environment. In the Genre Classification task, two approaches are used: Language Modeling, in which a transition probabilities matrix is created for each type of track (Melody, Harmony, Bass and Drums) and also for each genre; and an approach based on Neural Networks, where a vector of numeric descriptors is extracted from each track (Melody, Harmony, Bass and Drums) and fed to a Neural Network Classifier. Six MIDI Music Corpora were assembled for the experiments, from six different genres, Blues, Country, Jazz, Metal, Punk and Rock. These genres were selected because all of them have the same base instruments, such as bass, drums, piano or guitar. Also, the genres chosen share some characteristics between them, so that the classification isn't trivial, and tests the classifiers robustness. Track Classification experiments using all descriptors and best descriptors were made, showing that using all descriptors is a wrong approach, as there are descriptors which confuse the classifier. Using carefully selected descriptors proved to be the best way to classify these MIDI tracks. Genre Classification experiments showed that the Single-Instrument Classifiers achieved the best results. Four genres achieved higher than 80% success rates: Jazz, Country, Metal and Punk. Future work includes: genetic algorithms; structurize tracks and songs; merge all presented classifiers into one full Automatic Genre Classification System
24
Osório, Fernando Santos. "Inss : un système hybride neuro-symbolique pour l'apprentissage automatique constructif." Grenoble INPG, 1998. https://tel.archives-ouvertes.fr/tel-00004899.
Full textAbstract:
Plusieurs méthodes ont été développées par l'Intelligence Artificielle pour reproduire certains aspects de l'intelligence humaine. Ces méthodes permettent de simuler les processus de raisonnement en s'appuyant sur les connaissances de base disponibles. Chaque méthode comporte des points forts, mais aussi des limitations. La réalisation de systèmes hybrides est une démarche courante Qui permet de combiner les points forts de chaque approche, et d'obtenir ainsi des performances plus élevées ou un champ d'application plus large. Un autre aspect très important du développement des systèmes hybrides intelligents est leur capacité d'acquérir de nouvelles connaissances à partir de plusieurs sources différentes et de les faire évoluer. Dans cette thèse, nous avons développé des recherches sur les systèmes hybrides neuro-symboliques, et en particulier sur l'acquisition incrémentale de connaissances à partir de connaissances théoriques (règles) et empiriques (exemples). Un nouveau système hybride, nommé système INSS - Incremental Neuro-Symbolic System, a été étudié et réalisé. Ce système permet le transfert de connaissances déclaratives (règles symboliques) d'un module symbolique vers un module connexionniste (réseau de neurones artificiel - RNA) à travers un convertisseur de règles en réseau. Les connaissances du réseau ainsi obtenu sont affinées par un processus d'apprentissage à partir d'exemples. Ce raffinement se fait soit par ajout de nouvelles connaissances, soit par correction des incohérences, grâce à l'utilisation d'un réseau constructif de type Cascade-Correlation. Une méthode d'extraction incrémentale de règles a été intégrée au système INSS, ainsi que des algorithmes de validation des connaissances qui ont permis de mieux coupler les modules connexionniste et symbolique. Le système d'apprentissage automatique INSS a été conçu pour l'acquisition constructive (incrémentale) de connaissances. Le système a été testé sur plusieurs applications, en utilisant des problèmes académiques et des problèmes réels (diagnostic médical, modélisation cognitive et contrôle d'un robot autonome). Les résultats montrent que le système INSS a des performances supérieures et de nombreux avantages par rapport aux autres systèmes hybrides du même typeVarious Artificial Intelligence methods have been developed to reproduce intelligent human behaviour. These methods allow to reproduce some human reasoning process using the available knowledge. Each method has its advantages, but also some drawbacks. Hybrid systems combine different approaches in order to take advantage of their respective strengths. These hybrid intelligent systems also present the ability to acquire new knowledge from different sources and so to improve their application performance. This thesis presents our research in the field of hybrid neuro-symbolic systems, and in particular the study of machine learning tools used for constructive knowledge acquisition. We are interested in the automatic acquisition of theoretical knowledge (rules) and empirical knowledge (examples). We present a new hybrid system we implemented: INSS - Incremental Neuro-Symbolic System. This system allows knowledge transfer from the symbolic module to the connectionist module (Artificial Neural Network - ANN), through symbolic rule compilation into an ANN. We can refine the initial ANN knowledge through neural learning using a set of examples. The incremental ANN learning method used, the Cascade-Correlation algorithm, allows us to change or to add new knowledge to the network. Then, the system can also extract modified (or new) symbolic rules from the ANN and validate them. INSS is a hybrid machine learning system that implements a constructive knowledge acquisition method. We conclude by showing the results we obtained with this system in different application domains: ANN artificial problems(The Monk's Problems), computer aided medical diagnosis (Toxic Comas), a cognitive modelling task (The Balance Scale Problem) and autonomous robot control. The results we obtained show the improved performance of INSS and its advantages over others hybrid neuro-symbolic systems
25
Michulke, Daniel. "Evaluation Functions in General Game Playing." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2012. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-90566.
Full textAbstract:
While in traditional computer game playing agents were designed solely for the purpose of playing one single game, General Game Playing is concerned with agents capable of playing classes of games. Given the game's rules and a few minutes time, the agent is supposed to play any game of the class and eventually win it.
Since the game is unknown beforehand, previously optimized data structures or human-provided features are not applicable. Instead, the agent must derive a strategy on its own.
One approach to obtain such a strategy is to analyze the game rules and create a state evaluation function that can be subsequently used to direct the agent to promising states in the match.
In this thesis we will discuss existing methods and present a general approach on how to construct such an evaluation function.
Each topic is discussed in a modular fashion and evaluated along the lines of quality and efficiency, resulting in a strong agent.
26
Bader, Sebastian [Verfasser]. "Neural-symbolic integration / eingereicht von Sebastian Bader." 2009. http://d-nb.info/1008183652/34.
Full text
27
Ribeiro, Manuel António de Melo Chinopa de Sousa. "Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies." Master's thesis, 2020. http://hdl.handle.net/10362/113651.
Full textAbstract:
Artificial neural networks have been the key to solve a variety of different problems.
However, neural network models are still essentially regarded as black boxes, since they
do not provide any human-interpretable evidence as to why they output a certain re sult. In this dissertation, we address this issue by leveraging on ontologies and building
small classifiers that map a neural network’s internal representations to concepts from
an ontology, enabling the generation of symbolic justifications for the output of neural
networks. Using two image classification problems as testing ground, we discuss how to
map the internal representations of a neural network to the concepts of an ontology, exam ine whether the results obtained by the established mappings match our understanding
of the mapped concepts, and analyze the justifications obtained through this method.
28
Hostičková, Iva. "Vývoj paradigmat výzkumu umělé inteligence." Master's thesis, 2014. http://www.nusl.cz/ntk/nusl-332251.
Full textAbstract:
(in English): The purpose of this thesis is to describe developments of research in the field of artificial intelligence, from the point of view reflecting changes in current paradigms, and to analyze contemporary tendencies. This thesis systemically places the paradigm term into contexts of theoretical sciences and it explains in what way the term is being used. Further, the thesis describes artificial intelligence and several selected components. The thesis researches the basic paradigms of artificial intelligence - the symbolic and connectionistic paradigm, and is also researching new approaches and analyzing their beginnings and important development periods. The thesis analyzes reasons that were behind these developments. In addition to questions related to technical developments, financial support of selected research played an important role. The closing part of the thesis also analyzes reasons of current artificial intelligence expansion, worries connected to this expansion, and current research trends.
29
Bernardo, Alexandre Miguel Entradas. "Features for the Classification and Clustering of Music in Symbolic Format." Master's thesis, 2008. http://hdl.handle.net/10451/14010.
Full textAbstract:
This document describes the work carried out under the discipline of Computing
Engineering Project of the Computer Engineering Master, Sciences Faculty of the
Lisbon University.
Music Information Retrieval is, nowadays, a highly active branch of research
and development in the computer science field, and focuses several topics, including
music genre classification.
The work presented in this paper focus on Track and Genre Classification of
music stored using MIDI format,
To address the problem of MIDI track classification, we extract a set of descriptors
that are used to train a classifier implemented by a Neural Network, based on
the pitch levels and durations that describe each track. Tracks are classified into four
classes: Melody, Harmony, Bass and Drums. In order to characterize the musical
content from each track, a vector of numeric descriptors, normally known as shallow
structure description, is extracted. Then they are used as inputs for the classifier
which was implemented in the Matlab environment.
In the Genre Classification task, two approaches are used: Language Modeling,
in which a transition probabilities matrix is created for each type of track (Melody,
Harmony, Bass and Drums) and also for each genre; and an approach based on
Neural Networks, where a vector of numeric descriptors is extracted from each track
(Melody, Harmony, Bass and Drums) and fed to a Neural Network Classifier.
Six MIDI Music Corpora were assembled for the experiments, from six different
genres, Blues, Country, Jazz, Metal, Punk and Rock. These genres were selected
because all of them have the same base instruments, such as bass, drums, piano or
guitar. Also, the genres chosen share some characteristics between them, so that
the classification isn’t trivial, and tests the classifiers robustness.
Track Classification experiments using all descriptors and best descriptors were
made, showing that using all descriptors is a wrong approach, as there are descriptors
which confuse the classifier. Using carefully selected descriptors proved to be the
best way to classify these MIDI tracks.
Genre Classification experiments showed that the Single-Instrument Classifiers
achieved the best results. Four genres achieved higher than 80% success rates: Jazz,
Country, Metal and Punk.
Future work includes: genetic algorithms; structurize tracks and songs; merge
all presented classifiers into one full Automatic Genre Classification System.