Dissertations / Theses on the topic 'Computational Learning Sciences'
To see the other types of publications on this topic, follow the link: Computational Learning Sciences.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Computational Learning Sciences.'
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
Grover, Ishaan. "A semantics based computational model for word learning." Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/120694.
Abstract:
Thesis: S.M., Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2018.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 73-77).
Studies have shown that children's early literacy skills can impact their ability to achieve academic success, attain higher education and secure employment later in life. However, lack of resources and limited access to educational content causes a "knowledge gap" between children that come from different socio-economic backgrounds. To solve this problem, there has been a recent surge in the development of Intelligent Tutoring Systems (ITS) to provide learning benefits to children. However, before providing new content, an ITS must assess a child's existing knowledge. Several studies have shown that children learn new words by forming semantic relationships with words they already know. Human tutors often implicitly use semantics to assess a tutee's word knowledge from partial and noisy data. In this thesis, I present a cognitively inspired model that uses word semantics (semantics-based model) to make inferences about a child's vocabulary from partial information about their existing vocabulary. Using data from a one-to-one learning intervention between a robotic tutor and 59 children, I show that the proposed semantics-based model outperforms (on average) models that do not use word semantics (semantics-free models). A subject level analysis of results reveals that different models perform well for different children, thus motivating the need to combine predictions. To this end, I present two methods to combine predictions from semantics-based and semantics-free models and show that these methods yield better predictions of a child's vocabulary knowledge. Finally, I present an application of the semantics-based model to evaluate if a learning intervention was successful in teaching children new words while enhancing their semantic understanding. More concretely, I show that a personalized word learning intervention with a robotic tutor is better suited to enhance children's vocabulary when compared to a non-personalized intervention. These results motivate the use of semantics-based models to assess children's knowledge and build ITS that maximize children's semantic understanding of words.
"This research was supported by NSF IIP-1717362 and NSF IIS-1523118"--Page 10.
by Ishaan Grover.
S.M.
2
Kim, Richard S. M. Massachusetts Institute of Technology. "A computational model of moral learning for autonomous vehicles." Thesis, Massachusetts Institute of Technology, 2018. https://hdl.handle.net/1721.1/122897.
Abstract:
Thesis: S.M., Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2018Cataloged from PDF version of thesis.
Includes bibliographical references (pages 75-81).
We face a future of delegating many important decision making tasks to artificial intelligence (AI) systems as we anticipate widespread adoption of autonomous systems such as autonomous vehicles (AV). However, recent string of fatal accidents involving AV reminds us that delegating certain decisions making tasks have deep ethical complications. As a result, building ethical AI agent that makes decisions in line with human moral values has surfaced as a key challenge for Al researchers. While recent advances in deep learning in many domains of human intelligence suggests that deep learning models will also pave the way for moral learning and ethical decision making, training a deep learning model usually encompasses use of large quantities of human-labeled training data. In contrast to deep learning models, research in human cognition of moral learning theorizes that the human mind is capable of learning moral values from a few, limited observations of moral judgments of other individuals and apply those values to make ethical decisions in a new and unique moral dilemma. How can we leverage the insights that we have about human moral learning to design AI agents that can rapidly infer moral values of human it interacts with? In this work, I explore three cognitive mechanisms - abstraction, society-individual dynamics, and response time analysis - to demonstrate how these mechanisms contribute to rapid inference of moral values from limited number of observed data. I propose two Bayesian cognitive models to express these mechanisms using hierarchical Bayesian modeling framework and use large-scale ethical judgments from Moral Machine to empirically demonstrate the contributions of these mechanisms to rapid inference of individual preferences and biases in ethical decision making.
by Richard Kim.
S.M.
S.M. Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences
3
Fusté, Lleixà Anna. "Hypercubes : learning computational thinking through embodied spatial programming in augmented reality." Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/120690.
Abstract:
Thesis: S.M., Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2018.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 116-120).
Computational thinking has been described as a basic skill that should be included in the educational curriculum. Several online screen-based platforms for learning computational thinking have been developed during the past decades. In this thesis we propose the concept of Embodied Spatial Programming as a new and potentially improved programming paradigm for learning computational thinking in space. We have developed HyperCubes, an example Augmented Reality authoring platform that makes use of this paradigm. With a set of qualitative user studies we have assessed the engagement levels and the potential learning outcomes of the application. Through space, the physical environment, creativity and play the user is able to tinker with basic programming concepts that can lead to a better adoption of computational thinking skills.
by Anna Fusté Lleixà.
S.M.
4
Dasgupta, Sayamindu. "Learning with data : a toolkit to democratize the computational exploration of data." Thesis, Massachusetts Institute of Technology, 2012. http://hdl.handle.net/1721.1/78203.
Abstract:
Thesis (S.M.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2012.Cataloged from PDF version of thesis.
Includes bibliographical references (p. 93-95).
This thesis explores the space of programming with data, focusing on the data-ecosystem opened up by the Internet and Cloud technologies. The central argument of this thesis is that the act of democratizing programmatic access to online data can further unleash the generative powers of this emerging ecosystem, and enable explorations of a new set of concepts and powerful ideas. To establish the validity of this argument, this thesis introduces a learning framework for the computational exploration of online data, a system that enables children to program with online data, and then finally describes a study of children using the system to explore wide variety of creative possibilities, as well as important computational concepts and powerful ideas around data.
by Sayamindu Dasgupta.
S.M.
5
Roque, Ricarose Vallarta. "Family creative learning : designing structures to engage kids and parents as computational creators." Thesis, Massachusetts Institute of Technology, 2016. http://hdl.handle.net/1721.1/107577.
Abstract:
Thesis: Ph. D., Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2016.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 127-132).
The ability to create, design, and express oneself with technology is an important fluency for full participation in today's digitally mediated society. Social support can play a major role in engaging and deepening what young people can learn and do with technology. In particular, parents can play many roles, such as being collaborators, resource providers, and co-learners with their kids. In this dissertation, I explore the possibilities of engaging kids and their families as computational creators - providing opportunities and support to enable them to create things they care about with computing, to see themselves as creators, and to imagine the ways they can shape their world. I especially focus on families with limited access to resources and social support around computing. I describe the design of a community-based outreach program called Family Creative Learning, which invites kids, their families, and other families in their community to create and learn together using creative technologies. I use a qualitative approach to document the complex and diverse learning experiences of families. Through studies of family participation, I examine how kids and their parents supported one another and how the Family Creative Learning environment, activities, tools, and facilitation supported families in their development as computational creators. As families built projects, they also built perspectives in how they saw themselves, each other, and computing - developing identities as computational creators.
by Ricarose Roque.
Ph. D.
6
Vosoughi, Soroush. "Interactions of caregiver speech and early word learning in the Speechome corpus : computational explorations." Thesis, Massachusetts Institute of Technology, 2010. http://hdl.handle.net/1721.1/62082.
Abstract:
Thesis (S.M.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2010.Cataloged from PDF version of thesis.
Includes bibliographical references (p. 107-110).
How do characteristics of caregiver speech contribute to a child's early word learning? What is the relationship between a child's language development and caregivers' speech? Motivated by these general questions, this thesis comprises a series of computational studies on the fined-grained interactions of caregiver speech and one child's early linguistic development, using the naturalistic, high-density longitudinal corpus collected for the Human Speechome Project. The child's first productive use of a word was observed at about 11 months, totaling 517 words by his second birthday. Why did he learn those 517 words at the precise ages that he did? To address this specific question, we examined the relationship of the child's vocabulary growth to prosodic and distributional features of the naturally occurring caregiver speech to which the child was exposed. We measured fundamental frequency, intensity, phoneme duration, word usage frequency, word recurrence and mean length of utterances (MLU) for over one million words of caregivers' speech. We found significant correlations between all 6 variables and the child's age of acquisition (AoA) for individual words, with the best linear combination of these variables producing a correlation of r = -. 55(p < .001). We then used these variables to obtain a model of word acquisition as a function of caregiver input speech. This model was able to accurately predict the AoA of individual words within 55 days of their true AoA. We next looked at the temporal relationships between caregivers' speech and the child's lexical development. This was done by generating time-series for each variables for each caregiver, for each word. These time-series were then time-aligned by AoA. This analysis allowed us to see whether there is a consistent change in caregiver behavior for each of the six variables before and after the AoA of individual words. The six variables in caregiver speech all showed significant temporal relationships with the child's lexical development, suggesting that caregivers tune the prosodic and distributional characteristics of their speech to the linguistic ability of the child. This tuning behavior involves the caregivers progressively shortening their utterance lengths, becoming more redundant and exaggerating prosody more when uttering particular words as the child gets closer to the AoA of those words and reversing this trend as the child moves beyond the AoA. This "tuning" behavior was remarkably consistent across caregivers and variables, all following a very similar pattern. We found significant correlations between the patterns of change in caregiver behavior for each of the 6 variables and the AoA for individual words, with their best linear combination producing a correlation of r = -. 91(p < .001). Though the underlying cause of this strong correlation will require further study, it provides evidence of a new kind for fine-grained adaptive behavior by the caregivers in the context of child language development.
by Soroush Vosoughi.
S.M.
7
Hooper, Paula Kay 1961. "They have their own thoughts : children's learning of computational ideas from a cultural perspective." Thesis, Massachusetts Institute of Technology, 1998. http://hdl.handle.net/1721.1/41022.
8
Wagner, Alex Handler. "Computational methods for identification of disease-associated variations in exome sequencing." Diss., University of Iowa, 2014. https://ir.uiowa.edu/etd/1513.
Abstract:
The explosive growth in the ability to sequence DNA due to next-generation sequencing (NGS) technologies has brought an unprecedented ability to characterize an individual's exome inexpensively. This ability provides clinicians with additional tools to evaluate the likely genetic factors underlying heritable diseases. With this added capacity comes a need to identify relationships between the genetic variations observed in a patient and the disease with which the patient presents. This dissertation focuses on computational techniques to inform molecular diagnostics from NGS data. The techniques focus on three distinct domains in the characterization of disease-associated variants from exome sequencing.
First, strategies for producing complete and non-artifactual candidate variant lists are discussed. The process of converting patient DNA to a list of variants from the reference genome is very complex, and numerous modes of error may be introduced during the process. For this, a Random Forest classifier was built to capture biases in a laboratory variant calling pipeline, and a C4.5 decision tree was built to enable discovery of thresholds for false positive reduction. Additionally, a strategy for augmenting exome capture experiments through evaluation of RNA-sequencing is discussed.
Second, a novel positive and unlabeled learning for prioritization (PULP) strategy is proposed to identify candidate variants most likely to be associated with a patient's disease. Using a number of publicly available data sources, PULP ranks genes according to how alike they are to previously discovered disease genes. This strategy is evaluated on a number of candidate lists from the literature, and demonstrated to significantly enrich ordered candidate variants lists for likely disease-associated variants.
Finally, the Training for Recognition and Integration of Phenotypes in Ocular Disease (TRIPOD) web utility is introduced as a means of simultaneously training and learning from clinicians about heritable ocular diseases. This tool currently contains a number of case studies documenting a wide range of diseases, and challenges trainees to virtually diagnose patients based on presented image data. Annotations by trainee and expert alike are used to construct rich phenotypic profiles for patients with known disease genotypes.
The strategies presented in this dissertation are specifically applicable to heritable retinal dystrophies, and have resulted in a number of improvements to the accurate molecular diagnosis of patient diseases. However, these works also provide a generalizable framework for disease-associated variant identification in any heritable, genetically heterogeneous disease, and represent the ongoing challenge of accurate diagnosis in the information age.
9
Bodily, Paul Mark. "Machine Learning for Inspired, Structured, Lyrical Music Composition." BYU ScholarsArchive, 2018. https://scholarsarchive.byu.edu/etd/6930.
Abstract:
Computational creativity has been called the "final frontier" of artificial intelligence due to the difficulty inherent in defining and implementing creativity in computational systems. Despite this difficulty computer creativity is becoming a more significant part of our everyday lives, in particular music. This is observed in the prevalence of music recommendation systems, co-creational music software packages, smart playlists, and procedurally-generated video games. Significant progress can be seen in the advances in industrial applications such as Spotify, Pandora, Apple Music, etc., but several problems persist. Of more general interest, however, is the question of whether or not computers can exhibit autonomous creativity in music composition. One of the primary challenges in this endeavor is enabling computational systems to create music that exhibits global structure, that can learn structure from data, and which can effectively incorporate autonomy and intention. We seek to address these challenges in the context of a modular machine learning framework called hierarchical Bayesian program learning (HBPL). Breaking the problem of music composition into smaller pieces, we focus primarily on developing machine learning models that solve the problems related to structure. In particular we present an adaptation of non-homogenous Markov models that enable binary constraints and we present a structural learning model, the multiple Smith-Waterman (mSW) alignment method, which extends sequence alignment techniques from bioinformatics. To address the issue of intention, we incorporate our work on structured sequence generation into a full-fledged computational creative system called Pop* which we show through various evaluative means to possess to varying extents the characteristics of creativity and also creativity itself.
10
Bhattacharya, Sanmitra. "Computational methods for mining health communications in web 2.0." Diss., University of Iowa, 2014. https://ir.uiowa.edu/etd/4576.
Abstract:
Data from social media platforms are being actively mined for trends and patterns of interests. Problems such as sentiment analysis and prediction of election outcomes have become tremendously popular due to the unprecedented availability of social interactivity data of different types. In this thesis we address two problems that have been relatively unexplored. The first problem relates to mining beliefs, in particular health beliefs, and their surveillance using social media. The second problem relates to investigation of factors associated with engagement of U.S. Federal Health Agencies via Twitter and Facebook.
In addressing the first problem we propose a novel computational framework for belief surveillance. This framework can be used for 1) surveillance of any given belief in the form of a probe, and 2) automatically harvesting health-related probes. We present our estimates of support, opposition and doubt for these probes some of which represent true information, in the sense that they are supported by scientific evidence, others represent false information and the remaining represent debatable propositions. We show for example that the levels of support in false and debatable probes are surprisingly high. We also study the scientific novelty of these probes and find that some of the harvested probes with sparse scientific evidence may indicate novel hypothesis. We also show the suitability of off-the-shelf classifiers for belief surveillance. We find these classifiers are quite generalizable and can be used for classifying newly harvested probes. Finally, we show the ability of harvesting and tracking probes over time. Although our work is focused in health care, the approach is broadly applicable to other domains as well.
For the second problem, our specific goals are to study factors associated with the amount and duration of engagement of organizations. We use negative binomial hurdle regression models and Cox proportional hazards survival models for these. For Twitter, the hurdle analysis shows that presence of user-mention is positively associated with the amount of engagement while negative sentiment has inverse association. Content of tweets is also equally important for engagement. The survival analyses indicate that engagement duration is positively associated with follower count. For Facebook, both hurdle and survival analyses show that number of page likes and positive sentiment are correlated with higher and prolonged engagement while few content types are negatively correlated with engagement. We also find patterns of engagement that are consistent across Twitter and Facebook.
11
Svensson, Frida. "Scalable Distributed Reinforcement Learning for Radio Resource Management." Thesis, Linköpings universitet, Tillämpad matematik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-177822.
Abstract:
There is a large potential for automation and optimization in radio access networks (RANs) using a data-driven approach to efficiently handle the increase in complexity due to the steep growth in traffic and new technologies introduced with the development of 5G. Reinforcement learning (RL) has natural applications in RAN control loops such as link adaptation, interference management and power control at different timescales commonly occurring in the RAN context. Elevating the status of data-driven solutions in RAN and building a new, scalable, distributed and data-friendly RAN architecture will be needed to competitively tackle the challenges of coming 5G networks. In this work, we propose a systematic, efficient and robust methodology for applying RL on different control problems. Firstly, the proposed methodology is evaluated using a well-known control problem. Then, it is adapted to a real-world RAN scenario. Extensive simulation results are provided to show the effectiveness and potential of the proposed approach. The methodology was successfully created but results on a RAN-simulator were not matureDet finns en stor potential automatisering och optimering inom radionätverk (RAN, radio access network) genom att använda datadrivna lösningar för att på ett effektivt sätt hantera den ökade komplexiteten på grund av trafikökningar and nya teknologier som introducerats i samband med 5G. Förstärkningsinlärning (RL, reinforcement learning) har naturliga kopplingar till reglerproblem i olika tidsskalor, såsom länkanpassning, interferenshantering och kraftkontroll, vilket är vanligt förekommande i radionätverk. Att förhöja statusen på datadrivna lösningar i radionätverk kommer att vara nödvändigt för att hantera utmaningarna som uppkommer med framtida 5G nätverk. I detta arbete föreslås vi en syetematisk metodologi för att applicera RL på ett reglerproblem. I första hand används den föreslagna metodologin på ett välkänt reglerporblem. Senare anpassas metodologin till ett äkta RAN-scenario. Arbetet inkluderar utförliga resultat från simuleringar för att visa effektiviteten och potentialen hos den föreslagna metoden. En lyckad metodologi skapades men resultaten på RAN-simulatorn saknade mognad.
12
Schenkel, Timmy, Oliver Ringhage, and Nicklas Branding. "A Comparative Study of Facial Recognition Techniques : With focus on low computational power." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17216.
Abstract:
Facial recognition is an increasingly popular security measure in scenarios with low computational power, such as phones and Raspberry Pi’s. There are many facial recognition techniques available. The aim is to compare three such techniques in both performance and time metrics. An experiment was conducted to compare the facial recognition techniques Convolutional Neural Network (CNN), Eigenface with the classifiers K-Nearest Neighbors (KNN) and support vector machines (SVM) and Fisherface with the classifiers KNN and SVM under the same conditions with a limited version of the LFW dataset. The Python libraries scikit-learn and OpenCV as well as the CNN implementation FaceNet were used. The results show that the CNN implementation of FaceNet is the best technique in all metrics except for prediction time. FaceNet achieved an F-score of 100% while the OpenCV implementation of Eigenface using SVM scored the worst at 15.5%. The technique with the lowest prediction time was the scikit-learn implementation of Fisherface with SVM.
13
DiSalvo, Elizabeth (Betsy). "Glitch game testers: the design and study of a learning environment for computational production with young African American males." Diss., Georgia Institute of Technology, 2012. http://hdl.handle.net/1853/43646.
Abstract:
The implementation of a learning environment for young African American males, called the Glitch Game Testers, was launched in 2009. The development of this program was based on formative work that looked at the contrasting use of digital games between young African American males and individuals who chose to become computer science majors. Through analysis of cultural values and digital game play practices, the program was designed to intertwine authentic game development practices and computer science learning. The resulting program employed 25 African American male high school students to test pre-release digital games full-time in the summer and part-time in the school year, with an hour of each day dedicated to learning introductory computer science. Outcomes for persisting in computer science education are remarkable; of the 16 participants who had graduated from high school as of 2012, 12 have gone on to school in computing-related majors. These outcomes, and the participants' enthusiasm for engaging in computing, are in sharp contrast to the crisis in African American male education and learning motivation. The research presented in this dissertation discusses the formative research that shaped the design of Glitch, the evaluation of the implementation of Glitch, and a theoretical investigation of the way in which participants navigated conflicting motivations in learning environments.
14
Ozturel, Adnan Ismet. "A Computational Model Of Social Dynamics Of Musical Agreement." Master's thesis, METU, 2011. http://etd.lib.metu.edu.tr/upload/12613693/index.pdf.
Abstract:
Semiotic dynamics and computational evolutionary musicology literature investigate emergence and evolution of linguistic and musical conventions by using computational multi-agent complex adaptive system models. This thesis proposes a new computational evolutionary musicology model, by altering previous models of familiarity based musical interactions that
try to capture evolution of songs as a co-evolutionary process through mate selection. The proposed modified familiarity game models a closed community of agents, where individuals of the society interact with each other just by using their musical expectations. With this novel methodology, it is found that constituent agents can form a musical agreement by agreeing on a shared bi-gram musical expectation scheme. This convergence is attained in a self-organizing fashion and throughout this process significant usage of n-gram melodic lines become observable. Furthermore, modified familiarity game dynamics are investigated and it is concluded that convergence trends are dependent on simulation parameters.
15
Bilmes, Jeffrey Adam. "Timing is of the essence : perceptual and computational techniques for representing, learning, and reproducing expressive timing in percussive rhythm." Thesis, Massachusetts Institute of Technology, 1993. http://hdl.handle.net/1721.1/62091.
16
Sjöholm, Johan. "Probability as readability : A new machine learning approach to readability assessment for written Swedish." Thesis, Linköpings universitet, NLPLAB - Laboratoriet för databehandling av naturligt språk, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-78107.
Abstract:
This thesis explores the possibility of assessing the degree of readability of writtenSwedish using machine learning. An application using four levels of linguistic analysishas been implemented and tested with four different established algorithmsfor machine learning. The new approach has then been compared to establishedreadability metrics for Swedish. The results indicate that the new method workssignificantly better for readability classification of both sentences and documents.The system has also been tested with so called soft classification which returns aprobability for the degree of readability of a given text. This probability can thenbe used to rank texts according to probable degree of readability.Detta examensarbete utforskar möjligheterna att bedöma svenska texters läsbarhet med hjälp av maskininlärning. Ett system som använder fyra nivåer av lingvistisk analys har implementerats och testats med fyra olika etablerade algoritmer för maskininlärning. Det nya angreppssättet har sedan jämförts med etablerade läsbarhetsmått för svenska. Resultaten visar att den nya metoden fungerar markant bättre för läsbarhetsklassning av både meningar och hela dokument. Systemet har också testats med så kallad mjuk klassificering som ger ett sannolikhetsvärde för en given texts läsbarhetsgrad. Detta sannolikhetsvärde kan användas för rangordna texter baserad på sannolik läsbarhetsgrad.
17
Clark, Eric Michael. "Applications In Sentiment Analysis And Machine Learning For Identifying Public Health Variables Across Social Media." ScholarWorks @ UVM, 2019. https://scholarworks.uvm.edu/graddis/1006.
Abstract:
Twitter, a popular social media outlet, has evolved into a vast source of linguistic data, rich with opinion, sentiment, and discussion. We mined data from several public Twitter endpoints to identify content relevant to healthcare providers and public health regulatory professionals. We began by compiling content related to electronic nicotine delivery systems (or e-cigarettes) as these had become popular alternatives to tobacco products. There was an apparent need to remove high frequency tweeting entities, called bots, that would spam messages, advertisements, and fabricate testimonials. Algorithms were constructed using natural language processing and machine learning to sift human responses from automated accounts with high degrees of accuracy. We found the average hyperlink per tweet, the average character dissimilarity between each individual's content, as well as the rate of introduction of unique words were valuable attributes in identifying automated accounts. We performed a 10-fold Cross Validation and measured performance of each set of tweet features, at various bin sizes, the best of which performed with 97% accuracy. These methods were used to isolate automated content related to the advertising of electronic cigarettes. A rich taxonomy of automated entities, including robots, cyborgs, and spammers, each with different measurable linguistic features were categorized.
Electronic cigarette related posts were classified as automated or organic and content was investigated with a hedonometric sentiment analysis. The overwhelming majority (≈ 80%) were automated, many of which were commercial in nature. Others used false testimonials that were sent directly to individuals as a personalized form of targeted marketing. Many tweets advertised nicotine vaporizer fluid (or e-liquid) in various “kid-friendly” flavors including 'Fudge Brownie', 'Hot Chocolate', 'Circus Cotton Candy' along with every imaginable flavor of fruit, which were long ago banned for traditional tobacco products. Others offered free trials, as well as incentives to retweet and spread the post among their own network. Free prize giveaways were also hosted whose raffle tickets were issued for sharing their tweet. Due to the large youth presence on the public social media platform, this was evidence that the marketing of electronic cigarettes needed considerable regulation. Twitter has since officially banned all electronic cigarette advertising on their platform.
Social media has the capacity to afford the healthcare industry with valuable feedback from patients who reveal and express their medical decision-making process, as well as self-reported quality of life indicators both during and post treatment. We have studied several active cancer patient populations, discussing their experiences with the disease as well as survivor-ship. We experimented with a Convolutional Neural Network (CNN) as well as logistic regression to classify tweets as patient related. This led to a sample of 845 breast cancer survivor accounts to study, over 16 months. We found positive sentiments regarding patient treatment, raising support, and spreading awareness. A large portion of negative sentiments were shared regarding political legislation that could result in loss of coverage of their healthcare. We refer to these online public testimonies as “Invisible Patient Reported Outcomes” (iPROs), because they carry relevant indicators, yet are difficult to capture by conventional means of self-reporting. Our methods can be readily applied interdisciplinary to obtain insights into a particular group of public opinions. Capturing iPROs and public sentiments from online communication can help inform healthcare professionals and regulators, leading to more connected and personalized treatment regimens. Social listening can provide valuable insights into public health surveillance strategies.
18
Nyshadham, Chandramouli. "Materials Prediction Using High-Throughput and Machine Learning Techniques." BYU ScholarsArchive, 2019. https://scholarsarchive.byu.edu/etd/7735.
Abstract:
Predicting new materials through virtually screening a large number of hypothetical materials using supercomputers has enabled materials discovery at an accelerated pace. However, the innumerable number of possible hypothetical materials necessitates the development of faster computational methods for speedier screening of materials reducing the time of discovery. In this thesis, I aim to understand and apply two computational methods for materials prediction. The first method deals with a computational high-throughput study of superalloys. Superalloys are materials which exhibit high-temperature strength. A combinatorial high-throughput search across 2224 ternary alloy systems revealed 102 potential superalloys of which 37 are brand new, all of which we patented. The second computational method deals with a machine-learning (ML) approach and aims at understanding the consistency among five different state-of-the-art machine-learning models in predicting the formation enthalpy of 10 different binary alloys. The study revealed that although the five different ML models approach the problem uniquely, their predictions are consistent with each other and that they are all capable of predicting multiple materials simultaneously.My contribution to both the projects included conceiving the idea, performing calculations, interpreting the results, and writing significant portions of the two journal articles published related to each project. A follow-up work of both computational approaches, their impact, and future outlook of materials prediction are also presented.
19
Settelmeier, Jens. "Theoretical Fundamentals of Computational Proteomics and Deep Learning- Based Identification of Chimeric Mass Spectrometry Data." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-294322.
Abstract:
A complicating factor for peptide identification by MS/MS experiments is the presence of “chimeric” spectra where at least two precursor ions with similar retention time and mass co- elute in the mass spectrometer. This results in a spectrum that is a superposition of the spectra of the individual peptides. These chimeric spectra make peptide identification more difficult, so chimeric detection tools are needed to improve peptide identification rates. GLEAMS is a learned embedding algorithm for efficient joint analysis of millions of mass spectra. In this work, we first simulate chimeric spectra. Then we present a deep neural network- based classifier that learns to distinguish between chimeras and pure spectra. The result shows that GLEAMS captures a spectrum’s chimericness, which can lead to a higher protein identification rate in samples or support biomarker development processes and the like.En komplicerande faktor för peptididentifiering genom MS / MS- experiment är närvaron av “chimära” spektra eller “chimera”, där åtminstone två föregångare med liknande retentionstid och massa sameluerar in i masspektrometern och resulterar i ett spektrum som är en superposition av individuella spektra. Eftersom dessa chimära spektra gör identifieringen av peptider mer utmanande behövs ett detekteringsverktyg för att förbättra identifieringsgraden för peptider. I detta arbete fokuserade vi på GLEAMS, en lärd inbäddning för effektiv gemensam analys av miljontals masspektrum. Först simulerade vi chimära spektra. Sedan presenterar vi en ensembleklassificering baserad på olika maskininlärnings- och djupinlärningsmetoder som lär sig att skilja på simulerad chimera och rena spektra. Resultatet visar att GLEAM fångar “chimärheten” i ett spektrum, vilket kan leda till högre identifieringsgrad av protein samt ge stöd till utvecklingsprocesser för biomarkörer.
20
Strack, Robert. "Geometric Approach to Support Vector Machines Learning for Large Datasets." VCU Scholars Compass, 2013. http://scholarscompass.vcu.edu/etd/3124.
Abstract:
The dissertation introduces Sphere Support Vector Machines (SphereSVM) and Minimal Norm Support Vector Machines (MNSVM) as the new fast classification algorithms that use geometrical properties of the underlying classification problems to efficiently obtain models describing training data. SphereSVM is based on combining minimal enclosing ball approach, state of the art nearest point problem solvers and probabilistic techniques. The blending of the three speeds up the training phase of SVMs significantly and reaches similar (i.e., practically the same) accuracy as the other classification models over several big and large real data sets within the strict validation frame of a double (nested) cross-validation (CV). MNSVM is further simplification of SphereSVM algorithm. Here, relatively complex classification task was converted into one of the simplest geometrical problems -- minimal norm problem. This resulted in additional speedup compared to SphereSVM. The results shown are promoting both SphereSVM and MNSVM as outstanding alternatives for handling large and ultra-large datasets in a reasonable time without switching to various parallelization schemes for SVMs algorithms proposed recently. The variants of both algorithms, which work without explicit bias term, are also presented. In addition, other techniques aiming to improve the time efficiency are discussed (such as over-relaxation and improved support vector selection scheme). Finally, the accuracy and performance of all these modifications are carefully analyzed and results based on nested cross-validation procedure are shown.
21
Palaniappan, Krishnaveni. "Predicting "Essential" Genes in Microbial Genomes: A Machine Learning Approach to Knowledge Discovery in Microbial Genomic Data." NSUWorks, 2010. http://nsuworks.nova.edu/gscis_etd/268.
Abstract:
Essential genes constitute the minimal gene set of an organism that is indispensable for its survival under most favorable conditions. The problem of accurately identifying and predicting genes essential for survival of an organism has both theoretical and practical relevance in genome biology and medicine. From a theoretical perspective it provides insights in the understanding of the minimal requirements for cellular life and plays a key role in the emerging field of synthetic biology; from a practical perspective, it facilitates efficient identification of potential drug targets (e.g., antibiotics) in novel pathogens. However, characterizing essential genes of an organism requires sophisticated experimental studies that are expensive and time consuming. The goal of this research study was to investigate machine learning methods to accurately classify/predict "essential genes" in newly sequenced microbial genomes based solely on their genomic sequence data.
This study formulates the predication of essential genes problem as a binary classification problem and systematically investigates applicability of three different supervised classification methods for this task. In particular, Decision Tree (DT), Support Vector Machine (SVM), and Artificial Neural Network (ANN) based classifier models were constructed and trained on genomic features derived solely from gene sequence data of 14 experimentally validated microbial genomes whose essential genes are known. A set of 52 relevant genomic sequence derived features (including gene and protein sequence features, protein physio-chemical features and protein sub-cellular features) was used as input for the learners to learn the classifier models. The training and test datasets used in this study reflected between-class imbalance (i.e. skewed majority class vs. minority class) that is intrinsic to this data domain and essential genes prediction problem. Two imbalance reduction techniques (homology reduction and random under sampling of 50% of the majority class) were devised without artificially balancing the datasets and compromising classifier generalizability. The classifier models were trained and evaluated using 10-fold stratified cross validation strategy on both the full multi-genome datasets and its class imbalance reduced variants to assess their predictive ability of discriminating essential genes from non-essential genes. In addition, the classifiers were also evaluated using a novel blind testing strategy, called LOGO (Leave-One-Genome-Out) and LOTO (Leave-One-Taxon group-Out) tests on carefully constructed held-out datasets (both genome-wise (LOGO) and taxonomic group-wise (LOTO)) that were not used in training of the classifier models. Prediction performance metrics, accuracy, sensitivity, specificity, precision and area under the Receiver Operating Characteristics (AU-ROC) were assessed for DT, SVM and ANN derived models. Empirical results from 10 X 10-fold stratified cross validation, Leave-One-Genome-Out (LOGO) and Leave-One-Taxon group-Out (LOTO) blind testing experiments indicate SVM and ANN based models perform better than Decision Tree based models. On 10 X 10-fold cross validations, the SVM based models achieved an AU-ROC score of 0.80, while ANN and DT achieved 0.79 and 0.68 respectively. Both LOGO (genome-wise) and LOTO (taxonwise) blind tests revealed the generalization extent of these classifiers across different genomes and taxonomic orders.
This study empirically demonstrated the merits of applying machine learning methods to predict essential genes in microbial genomes by using only gene sequence and features derived from it. It also demonstrated that it is possible to predict essential genes based on features derived from gene sequence without using homology information. LOGO and LOTO Blind test results reveal that the trained classifiers do generalize across genomes and taxonomic boundaries and provide first critical estimate of predictive performance on microbial genomes. Overall, this study provides a systematic assessment of applying DT, ANN and SVM to this prediction problem.
An important potential application of this study will be to apply the resultant predictive model/approach and integrate it as a genome annotation pipeline method for comparative microbial genome and metagenome analysis resources such as the Integrated Microbial Genome Systems (IMG and IMG/M).
22
Gustavsson, Hanna, and Hanna Karlsson. "The Virtual Learning Environment : Patterns for Structuring Web based Teaching." Thesis, Blekinge Tekniska Högskola, Institutionen för programvaruteknik och datavetenskap, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4851.
Abstract:
Online education creates new demands on organization and structure in order to make use of its advantages with the technology for learning. Research in this area elucidates new possibilities with the computer as a medium, to individualize and make the learning more flexible. Meanwhile, the empirical study shows practical limitations, which affects the design of web-based teaching. As a result, we have started to develop a guideline, which describes these new possibilities and common problems with the new learning environment. We have structured the guideline by first defining the problem area and then giving recommendation or in some cases proposal of improving the technique. The purpose with the guideline is to illustrate and support teachers with knowledge and inspiration to make the design of this new form of education suitable in its practice.
23
Ganey, Raeesa. "Principal points, principal curves and principal surfaces." Master's thesis, University of Cape Town, 2015. http://hdl.handle.net/11427/15515.
Abstract:
The idea of approximating a distribution is a prominent problem in statistics. This dissertation explores the theory of principal points and principal curves as approximation methods to a distribution. Principal points of a distribution have been initially introduced by Flury (1990) who tackled the problem of optimal grouping in multivariate data. In essence, principal points are the theoretical counterparts of cluster means obtained by the k-means algorithm. Principal curves defined by Hastie (1984), are smooth one-dimensional curves that pass through the middle of a p-dimensional data set, providing a nonlinear summary of the data. In this dissertation, details on the usefulness of principal points and principal curves are reviewed. The application of principal points and principal curves are then extended beyond its original purpose to well-known computational methods like Support Vector Machines in machine learning.
24
Polianskii, Vladislav. "An Investigation of Neural Network Structure with Topological Data Analysis." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-238702.
Abstract:
Artificial neural networks at the present time gain notable popularity and show astounding results in many machine learning tasks. This, however, also results in a drawback that the understanding of the processes happening inside of learning algorithms decreases. In many cases, the process of choosing a neural network architecture for a problem comes down to selection of network layers by intuition and to manual tuning of network parameters. Therefore, it is important to build a strong theoretical base in this area, both to try to reduce the amount of manual work in the future and to get a better understanding of capabilities of neural networks. In this master thesis, the ideas of applying different topological and geometric methods for the analysis of neural networks were investigated. Despite the difficulties which arise from the novelty of the approach, such as limited amount of related studies, some promising methods of network analysis were established and tested on baseline machine learning datasets. One of the most notable results of the study reveals how neural networks preserve topological features of the data when it is projected into space with low dimensionality. For example, the persistence for MNIST dataset with added rotations of images gets preserved after the projection into 3D space with the use of simple autoencoders; on the other hand, autoencoders with a relatively high weight regularization parameter might be losing this ability.Artificiella neuronnät har för närvarande uppnått märkbar popularitet och visar häpnadsväckande resultat i många maskininlärningsuppgifter. Dock leder detta också till nackdelen att förståelsen av de processer som sker inom inlärningsalgoritmerna minskar. I många fall måste man använda intuition och ställa in parametrar manuellt under processen att välja en nätverksarkitektur. Därför är det viktigt att bygga en stark teoretisk bas inom detta område, både för att försöka minska manuellt arbete i framtiden och för att få en bättre förståelse för kapaciteten hos neuronnät. I detta examensarbete undersöktes idéerna om att tillämpa olika topologiska och geometriska metoder för analys av neuronnät. Många av svårigheterna härrör från det nya tillvägagångssättet, såsom en begränsad mängd av relaterade studier, men några lovande nätverksanalysmetoder upprättades och testades på standarddatauppsättningar för maskininlärning. Ett av de mest anmärkningsvärda resultaten av examensarbetet visar hur neurala nätverk bevarar de topologiska egenskaperna hos data när den projiceras till vektorrum med låg dimensionalitet. Till exempel bevaras den topologiska persistensen för MNIST-datasetet med tillagda rotationer av bilder efter projektion i ett tredimensionellt vektorrum med användning av en basal autoencoder; å andra sidan kan autoencoders med en relativt hög viktregleringsparameter förlora denna egenskap.
25
Middleton, Anthony M. "High-Performance Knowledge-Based Entity Extraction." NSUWorks, 2009. http://nsuworks.nova.edu/gscis_etd/246.
Abstract:
Human language records most of the information and knowledge produced by organizations and individuals. The machine-based process of analyzing information in natural language form is called natural language processing (NLP). Information extraction (IE) is the process of analyzing machine-readable text and identifying and collecting information about specified types of entities, events, and relationships.
Named entity extraction is an area of IE concerned specifically with recognizing and classifying proper names for persons, organizations, and locations from natural language. Extant approaches to the design and implementation named entity extraction systems include: (a) knowledge-engineering approaches which utilize domain experts to hand-craft NLP rules to recognize and classify named entities; (b) supervised machine-learning approaches in which a previously tagged corpus of named entities is used to train algorithms which incorporate statistical and probabilistic methods for NLP; or (c) hybrid approaches which incorporate aspects of both methods described in (a) and (b).
Performance for IE systems is evaluated using the metrics of precision and recall which measure the accuracy and completeness of the IE task. Previous research has shown that utilizing a large knowledge base of known entities has the potential to improve overall entity extraction precision and recall performance. Although existing methods typically incorporate dictionary-based features, these dictionaries have been limited in size and scope.
The problem addressed by this research was the design, implementation, and evaluation of a new high-performance knowledge-based hybrid processing approach and associated algorithms for named entity extraction, combining rule-based natural language parsing and memory-based machine learning classification facilitated by an extensive knowledge base of existing named entities. The hybrid approach implemented by this research resulted in improved precision and recall performance approaching human-level capability compared to existing methods measured using a standard test corpus. The system design incorporated a parallel processing system architecture with capabilities for managing a large knowledge base and providing high throughput potential for processing large collections of natural language text documents.
26
Tang, Yuchun. "Granular Support Vector Machines Based on Granular Computing, Soft Computing and Statistical Learning." Digital Archive @ GSU, 2006. http://digitalarchive.gsu.edu/cs_diss/5.
Abstract:
With emergence of biomedical informatics, Web intelligence, and E-business, new challenges are coming for knowledge discovery and data mining modeling problems. In this dissertation work, a framework named Granular Support Vector Machines (GSVM) is proposed to systematically and formally combine statistical learning theory, granular computing theory and soft computing theory to address challenging predictive data modeling problems effectively and/or efficiently, with specific focus on binary classification problems. In general, GSVM works in 3 steps. Step 1 is granulation to build a sequence of information granules from the original dataset or from the original feature space. Step 2 is modeling Support Vector Machines (SVM) in some of these information granules when necessary. Finally, step 3 is aggregation to consolidate information in these granules at suitable abstract level. A good granulation method to find suitable granules is crucial for modeling a good GSVM. Under this framework, many different granulation algorithms including the GSVM-CMW (cumulative margin width) algorithm, the GSVM-AR (association rule mining) algorithm, a family of GSVM-RFE (recursive feature elimination) algorithms, the GSVM-DC (data cleaning) algorithm and the GSVM-RU (repetitive undersampling) algorithm are designed for binary classification problems with different characteristics. The empirical studies in biomedical domain and many other application domains demonstrate that the framework is promising. As a preliminary step, this dissertation work will be extended in the future to build a Granular Computing based Predictive Data Modeling framework (GrC-PDM) with which we can create hybrid adaptive intelligent data mining systems for high quality prediction.
27
Chen, Xiujuan. "Computational Intelligence Based Classifier Fusion Models for Biomedical Classification Applications." Digital Archive @ GSU, 2007. http://digitalarchive.gsu.edu/cs_diss/26.
Abstract:
The generalization abilities of machine learning algorithms often depend on the algorithms’ initialization, parameter settings, training sets, or feature selections. For instance, SVM classifier performance largely relies on whether the selected kernel functions are suitable for real application data. To enhance the performance of individual classifiers, this dissertation proposes classifier fusion models using computational intelligence knowledge to combine different classifiers. The first fusion model called T1FFSVM combines multiple SVM classifiers through constructing a fuzzy logic system. T1FFSVM can be improved by tuning the fuzzy membership functions of linguistic variables using genetic algorithms. The improved model is called GFFSVM. To better handle uncertainties existing in fuzzy MFs and in classification data, T1FFSVM can also be improved by applying type-2 fuzzy logic to construct a type-2 fuzzy classifier fusion model (T2FFSVM). T1FFSVM, GFFSVM, and T2FFSVM use accuracy as a classifier performance measure. AUC (the area under an ROC curve) is proved to be a better classifier performance metric. As a comparison study, AUC-based classifier fusion models are also proposed in the dissertation. The experiments on biomedical datasets demonstrate promising performance of the proposed classifier fusion models comparing with the individual composing classifiers. The proposed classifier fusion models also demonstrate better performance than many existing classifier fusion methods. The dissertation also studies one interesting phenomena in biology domain using machine learning and classifier fusion methods. That is, how protein structures and sequences are related each other. The experiments show that protein segments with similar structures also share similar sequences, which add new insights into the existing knowledge on the relation between protein sequences and structures: similar sequences share high structure similarity, but similar structures may not share high sequence similarity.
28
Heath, Derrall L. "Using Perceptually Grounded Semantic Models to Autonomously Convey Meaning Through Visual Art." BYU ScholarsArchive, 2016. https://scholarsarchive.byu.edu/etd/6095.
Abstract:
Developing advanced semantic models is important in building computational systems that can not only understand language but also convey ideas and concepts to others. Semantic models can allow a creative image-producing-agent to autonomously produce artifacts that communicate an intended meaning. This notion of communicating meaning through art is often considered a necessary part of eliciting an aesthetic experience in the viewer and can thus enhance the (perceived) creativity of the agent. Computational creativity, a subfield of artificial intelligence, deals with designing computational systems and algorithms that either automatically create original and functional products, or that augment the ability of humans to do so. We present work on DARCI (Digital ARtist Communicating Intention), a system designed to autonomously produce original images that convey meaning. In order for DARCI to automatically express meaning through the art it creates, it must have its own semantic model that is perceptually grounded with visual capabilities.The work presented here focuses on designing, building, and incorporating advanced semantic and perceptual models into the DARCI system. These semantic models give DARCI a better understanding of the world and enable it to be more autonomous, to better evaluate its own artifacts, and to create artifacts with intention. Through designing, implementing, and studying DARCI, we have developed evaluation methods, models, frameworks, and theories related to the creative process that can be generalized to other domains outside of visual art. Our work on DARCI has even influenced the visual art community through several collaborative efforts, art galleries, and exhibits. We show that the DARCI system is successful at autonomously producing original art that is meaningful to human viewers. We also discuss insights that our efforts have contributed to the field of computational creativity.
29
Skone, Gwyn S. "Stratagems for effective function evaluation in computational chemistry." Thesis, University of Oxford, 2010. http://ora.ox.ac.uk/objects/uuid:8843465b-3e5f-45d9-a973-3b27949407ef.
Abstract:
In recent years, the potential benefits of high-throughput virtual screening to the drug discovery community have been recognized, bringing an increase in the number of tools developed for this purpose. These programs have to process large quantities of data, searching for an optimal solution in a vast combinatorial range. This is particularly the case for protein-ligand docking, since proteins are sophisticated structures with complicated interactions for which either molecule might reshape itself. Even the very limited flexibility model to be considered here, using ligand conformation ensembles, requires six dimensions of exploration - three translations and three rotations - per rigid conformation. The functions for evaluating pose suitability can also be complex to calculate. Consequently, the programs being written for these biochemical simulations are extremely resource-intensive. This work introduces a pure computer science approach to the field, developing techniques to improve the effectiveness of such tools. Their architecture is generalized to an abstract pattern of nested layers for discussion, covering scoring functions, search methods, and screening overall. Based on this, new stratagems for molecular docking software design are described, including lazy or partial evaluation, geometric analysis, and parallel processing implementation. In addition, a range of novel algorithms are presented for applications such as active site detection with linear complexity (PIES) and small molecule shape description (PASTRY) for pre-alignment of ligands. The various stratagems are assessed individually and in combination, using several modified versions of an existing docking program, to demonstrate their benefit to virtual screening in practical contexts. In particular, the importance of appropriate precision in calculations is highlighted.
30
Levin, Fredrik. "Simulating Artificial Recombination for a Deep Convolutional Autoencoder." Thesis, Uppsala universitet, Människans evolution, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-448312.
Abstract:
Population structure is an important field of study due to its importance in finding underlying genetics of various diseases.This is why this thesis has looked at a newly presented deep convolutional autoencoder that has been showing promising results when compared to the state-of-the-art method for quantifying genetic similarities within population structure. The main focus was to introduce data augmentation in the form of artificial diploid recombination to this autoencoder in an attempt to increase performance and robustness of the network structure. The training data for the network consist of arrays containing information about single-nucleotide polymorphisms present in an individual. Each instance of augmented data was simulated by randomising cuts based on the distance between the polymorphisms, and then creating a new array by alternating between the arrays of two randomised original data instances. Several networks were then trained using this data augmentation. The performance of the trained networks was compared to networks trained on only original data using several metrics. Both groups of networks had similar performance for most metrics. The main difference was that networks trained on only original data had a low genotype concordance on simulated data. This indicates an underlying risk using the original networks, which can be overcome by introducing the artificial recombination.
31
Källman, Britt-Marie, and Lenita Färje. "Kommunikationens redskap och språkets betydelse för analog programmering, ur ett sociokulturellt perspektiv." Thesis, Uppsala universitet, Institutionen för pedagogik, didaktik och utbildningsstudier, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-455542.
Abstract:
Studiens syfte är att bidra med kunskap om hur barn och pedagoger interagerar och kommunicerar i sagoberättande, samt undersöka om det finns en grund till datalogiskt tänkande i redan befintlig undervisning. Studien har utgått från det sociokulturella perspektivet där interaktionen mellan människor är grunden för lärandet, genom att observera sagostunder, som genomfördes med hjälp av flanotavlan och dess bilder. Som metod användes direktobservationer med semistrukturerat observationsschema, utformat från Interaction Process Analysis (IPA). Observationerna visade på att ord som förekommer inom analog programmering så som räkneord, kommandon, position och riktning också förekom i sagoberättandet, men användes inte för analog programmering.
32
Cockroft, Nicholas T. "Applications of Cheminformatics for the Analysis of Proteolysis Targeting Chimeras and the Development of Natural Product Computational Target Fishing Models." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu156596730476322.
33
Nalenz, Malte. "Horseshoe RuleFit : Learning Rule Ensembles via Bayesian Regularization." Thesis, Linköpings universitet, Statistik, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-130249.
Abstract:
This work proposes Hs-RuleFit, a learning method for regression and classification, which combines rule ensemble learning based on the RuleFit algorithm with Bayesian regularization through the horseshoe prior. To this end theoretical properties and potential problems of this combination are studied. A second step is the implementation, which utilizes recent sampling schemes to make the Hs-RuleFit computationally feasible. Additionally, changes to the RuleFit algorithm are proposed such as Decision Rule post-processing and the usage of Decision rules generated via Random Forest. Hs-RuleFit addresses the problem of finding highly accurate and yet interpretable models. The method shows to be capable of finding compact sets of informative decision rules that give a good insight in the data. Through the careful choice of prior distributions the horse-shoe prior shows to be superior to the Lasso in this context. In an empirical evaluation on 16 real data sets Hs-RuleFit shows excellent performance in regression and outperforms the popular methods Random Forest, BART and RuleFit in terms of prediction error. The interpretability is demonstrated on selected data sets. This makes the Hs-RuleFit a good choice for science domains in which interpretability is desired. Problems are found in classification, regarding the usage of the horseshoe prior and rule ensemble learning in general. A simulation study is performed to isolate the problems and potential solutions are discussed. Arguments are presented, that the horseshoe prior could be a good choice in other machine learning areas, such as artificial neural networks and support vector machines.
34
Chen, Xi. "Learning with Sparcity: Structures, Optimization and Applications." Research Showcase @ CMU, 2013. http://repository.cmu.edu/dissertations/228.
Abstract:
The development of modern information technology has enabled collecting data of unprecedented size and complexity. Examples include web text data, microarray & proteomics, and data from scientific domains (e.g., meteorology). To learn from these high dimensional and complex data, traditional machine learning techniques often suffer from the curse of dimensionality and unaffordable computational cost. However, learning from large-scale high-dimensional data promises big payoffs in text mining, gene analysis, and numerous other consequential tasks.
Recently developed sparse learning techniques provide us a suite of tools for understanding and exploring high dimensional data from many areas in science and engineering. By exploring sparsity, we can always learn a parsimonious and compact model which is more interpretable and computationally tractable at application time. When it is known that the underlying model is indeed sparse, sparse learning methods can provide us a more consistent model and much improved prediction performance. However, the existing methods are still insufficient for modeling complex or dynamic structures of the data, such as those evidenced in pathways of genomic data, gene regulatory network, and synonyms in text data.
This thesis develops structured sparse learning methods along with scalable optimization algorithms to explore and predict high dimensional data with complex structures. In particular, we address three aspects of structured sparse learning:
1. Efficient and scalable optimization methods with fast convergence guarantees for a wide spectrum of high-dimensional learning tasks, including single or multi-task structured regression, canonical correlation analysis as well as online sparse learning.
2. Learning dynamic structures of different types of undirected graphical models, e.g., conditional Gaussian or conditional forest graphical models.
3. Demonstrating the usefulness of the proposed methods in various applications, e.g., computational genomics and spatial-temporal climatological data. In addition, we also design specialized sparse learning methods for text mining applications, including ranking and latent semantic analysis.
In the last part of the thesis, we also present the future direction of the high-dimensional structured sparse learning from both computational and statistical aspects.
35
Lindblom, Rebecca. "News Value Modeling and Prediction using Textual Features and Machine Learning." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167062.
Abstract:
News value assessment has been done forever in the news media industry and is today often done in real-time without any documentation. Editors take a lot of different qualitative aspects into consideration when deciding what news stories will make it to the first page. This thesis explores how the complex news value assessment process can be translated into a quantitative model, and also how those news values can be predicted in an effective way using machine learning and NLP. Two models for news value were constructed, for which the correlation between modeled and manual news values was measured, and the results show that the more complex model gives a higher correlation. For prediction, different types of features are extracted, Random Forest and SVM are used, and the predictions are evaluated with accuracy, F1-score, RMSE, and MAE. Random Forest shows the best results for all metrics on all datasets, the best result being on the largest dataset, probably due to the smaller datasets having a less even distribution between classes.
36
Holmström, Oskar. "Exploring Transformer-Based Contextual Knowledge Graph Embeddings : How the Design of the Attention Mask and the Input Structure Affect Learning in Transformer Models." Thesis, Linköpings universitet, Artificiell intelligens och integrerade datorsystem, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-175400.
Abstract:
The availability and use of knowledge graphs have become commonplace as a compact storage of information and for lookup of facts. However, the discrete representation makes the knowledge graph unavailable for tasks that need a continuous representation, such as predicting relationships between entities, where the most probable relationship needs to be found. The need for a continuous representation has spurred the development of knowledge graph embeddings. The idea is to position the entities of the graph relative to each other in a continuous low-dimensional vector space, so that their relationships are preserved, and ideally leading to clusters of entities with similar characteristics. Several methods to produce knowledge graph embeddings have been created, from simple models that minimize the distance between related entities to complex neural models. Almost all of these embedding methods attempt to create an accurate static representation of each entity and relation. However, as with words in natural language, both entities and relations in a knowledge graph hold different meanings in different local contexts. With the recent development of Transformer models, and their success in creating contextual representations of natural language, work has been done to apply them to graphs. Initial results show great promise, but there are significant differences in archi- tecture design across papers. There is no clear direction on how Transformer models can be best applied to create contextual knowledge graph embeddings. Two of the main differences in previous work is how the attention mask is applied in the model and what input graph structures the model is trained on. This report explores how different attention masking methods and graph inputs affect a Transformer model (in this report, BERT) on a link prediction task for triples. Models are trained with five different attention masking methods, which to varying degrees restrict attention, and on three different input graph structures (triples, paths, and interconnected triples). The results indicate that a Transformer model trained with a masked language model objective has the strongest performance on the link prediction task when there are no restrictions on how attention is directed, and when it is trained on graph structures that are sequential. This is similar to how models like BERT learn sentence structure after being exposed to a large number of training samples. For more complex graph structures it is beneficial to encode information of the graph structure through how the attention mask is applied. There also seems to be some indications that the input graph structure affects the models’ capabilities to learn underlying characteristics in the knowledge graph that is trained upon.
37
Iqbal, Sumaiya. "Machine Learning based Protein Sequence to (un)Structure Mapping and Interaction Prediction." ScholarWorks@UNO, 2017. http://scholarworks.uno.edu/td/2379.
Abstract:
Proteins are the fundamental macromolecules within a cell that carry out most of the biological functions. The computational study of protein structure and its functions, using machine learning and data analytics, is elemental in advancing the life-science research due to the fast-growing biological data and the extensive complexities involved in their analyses towards discovering meaningful insights. Mapping of protein’s primary sequence is not only limited to its structure, we extend that to its disordered component known as Intrinsically Disordered Proteins or Regions in proteins (IDPs/IDRs), and hence the involved dynamics, which help us explain complex interaction within a cell that is otherwise obscured. The objective of this dissertation is to develop machine learning based effective tools to predict disordered protein, its properties and dynamics, and interaction paradigm by systematically mining and analyzing large-scale biological data.
In this dissertation, we propose a robust framework to predict disordered proteins given only sequence information, using an optimized SVM with RBF kernel. Through appropriate reasoning, we highlight the structure-like behavior of IDPs in disease-associated complexes. Further, we develop a fast and effective predictor of Accessible Surface Area (ASA) of protein residues, a useful structural property that defines protein’s exposure to partners, using regularized regression with 3rd-degree polynomial kernel function and genetic algorithm. As a key outcome of this research, we then introduce a novel method to extract position specific energy (PSEE) of protein residues by modeling the pairwise thermodynamic interactions and hydrophobic effect. PSEE is found to be an effective feature in identifying the enthalpy-gain of the folded state of a protein and otherwise the neutral state of the unstructured proteins. Moreover, we study the peptide-protein transient interactions that involve the induced folding of short peptides through disorder-to-order conformational changes to bind to an appropriate partner. A suite of predictors is developed to identify the residue-patterns of Peptide-Recognition Domains from protein sequence that can recognize and bind to the peptide-motifs and phospho-peptides with post-translational-modifications (PTMs) of amino acid, responsible for critical human diseases, using the stacked generalization ensemble technique. The involved biologically relevant case-studies demonstrate possibilities of discovering new knowledge using the developed tools.
38
Moussa, Ahmed S. "On learning and visualizing lexicographic preference trees." UNF Digital Commons, 2019. https://digitalcommons.unf.edu/etd/882.
Abstract:
Preferences are very important in research fields such as decision making, recommendersystemsandmarketing. The focus of this thesis is on preferences over combinatorial domains, which are domains of objects configured with categorical attributes. For example, the domain of cars includes car objects that are constructed withvaluesforattributes, such as ‘make’, ‘year’, ‘model’, ‘color’, ‘body type’ and ‘transmission’.Different values can instantiate an attribute. For instance, values for attribute ‘make’canbeHonda, Toyota, Tesla or BMW, and attribute ‘transmission’ can haveautomaticormanual. To this end,thisthesis studiesproblemsonpreference visualization and learning for lexicographic preference trees, graphical preference models that often are compact over complex domains of objects built of categorical attributes. Visualizing preferences is essential to provide users with insights into the process of decision making, while learning preferences from data is practically important, as it is ineffective to elicit preference models directly from users.
The results obtained from this thesis are two parts: 1) for preference visualization, aweb- basedsystem is created that visualizes various types of lexicographic preference tree models learned by a greedy learning algorithm; 2) for preference learning, a genetic algorithm is designed and implemented, called GA, that learns a restricted type of lexicographic preference tree, called unconditional importance and unconditional preference tree, or UIUP trees for short. Experiments show that GA achieves higher accuracy compared to the greedy algorithm at the cost of more computational time. Moreover, a Dynamic Programming Algorithm (DPA) was devised and implemented that computes an optimal UIUP tree model in the sense that it satisfies as many examples as possible in the dataset. This novel exact algorithm (DPA), was used to evaluate the quality of models computed by GA, and it was found to reduce the factorial time complexity of the brute force algorithm to exponential. The major contribution to the field of machine learning and data mining in this thesis would be the novel learning algorithm (DPA) which is an exact algorithm. DPA learns and finds the best UIUP tree model in the huge search space which classifies accurately the most number of examples in the training dataset; such model is referred to as the optimal model in this thesis. Finally, using datasets produced from randomly generated UIUP trees, this thesis presents experimental results on the performances (e.g., accuracy and computational time) of GA compared to the existent greedy algorithm and DPA.
39
Meuth, Ryan James. "Meta-learning computational intelligence architectures." Diss., Rolla, Mo. : Missouri University of Science and Technology, 2009. http://scholarsmine.mst.edu/thesis/pdf/Meuth_09007dcc80722172.pdf.
Abstract:
Thesis (Ph. D.)--Missouri University of Science and Technology, 2009.Vita. The entire thesis text is included in file. Title from title screen of thesis/dissertation PDF file (viewed January 5, 2010) Includes bibliographical references (p. 152-159).
40
Alabdulkareem, Ahmad. "Analyzing cities' complex socioeconomic networks using computational science and machine learning." Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/119325.
Abstract:
Thesis: Ph. D. in Computational Science & Engineering, Massachusetts Institute of Technology, Department of Civil and Environmental Engineering, 2018.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 133-141).
By 2050, it is expected that 66% of the world population will be living in cities. The urban growth explosion in recent decades has raised many questions concerning the evolutionary advantages of urbanism, with several theories delving into the multitude of benefits of such efficient systems. This thesis focuses on one important aspect of cities: their social dimension, and in particular, the social aspect of their complex socioeconomic fabric (e.g. labor markets and social networks). Economic inequality is one of the greatest challenges facing society today, in tandem with the eminent impact of automation, which can exacerbate this issue. The social dimension plays a significant role in both, with many hypothesizing that social skills will be the last bastion of differentiation between humans and machines, and thus, jobs will become mostly dominated by social skills. Using data-driven tools from network science, machine learning, and computational science, the first question I aim to answer is the following: what role do social skills play in today's labor markets on both a micro and macro scale (e.g. individuals and cities)? Second, how could the effects of automation lead to various labor dynamics, and what role would social skills play in combating those effects? Specifically, what are social skills' relation to career mobility? Which would inform strategies to mitigate the negative effects of automation and off-shoring on employment. Third, given the importance of the social dimension in cities, what theoretical model can explain such results, and what are its consequences? Finally, given the vulnerabilities for invading individuals' privacy, as demonstrated in previous chapters, how does highlighting those results affect people's interest in privacy preservation, and what are some possible solutions to combat this issue?
by Ahmad Alabdulkareem.
Ph. D. in Computational Science & Engineering
41
Mercier, Chloé. "Modéliser les processus cognitifs dans une tâche de résolution créative de problème : des approches symboliques à neuro-symboliques en sciences computationnelles de l'éducation." Electronic Thesis or Diss., Bordeaux, 2024. http://www.theses.fr/2024BORD0065.
Abstract:
L’intégration de compétences transversales telles que la créativité, la résolution de problèmes et la pensée informatique, dans les programmes d’enseignement primaire et secondaire, est un défi majeur dans le domaine de l’éducation aujourd’hui. Nous postulons que l’enseignement et l’évaluation de ces compétences transversales pourraient bénéficier d’une meilleure compréhension des comportements des apprenants dans des activités spécifiques qui requièrent ces compétences. A cette fin, les sciences computationnelles de l’apprentissage (computational learning sciences) sont un champ en émergence qui requiert l’étroite collaboration des neurosciences computationnelles et des sciences de l’éducation pour permettre l’évaluation des processus d’apprentissage. Nous nous concentrons sur une tâche de résolution créative de problème dans laquelle le sujet est amené à construire un “véhicule” en combinant des cubes robotiques modulaires. Dans le cadre d’une action de recherche exploratoire, nous proposons plusieurs approches s’appuyant sur des formalismes symboliques à neuro-symboliques, afin de spécifier une telle tâche et de modéliser les comportements et processus cognitifs sousjacents d’un sujet engagé dans cette tâche. Bien qu’étant à un stade très préliminaire, une telle formalisation semble prometteuse pour mieux comprendre les mécanismes complexes impliqués dans la résolution créative de problèmes à plusieurs niveaux : (i) la spécification du problème et les observables d’intérêt à collecter pendant la tâche ; (ii) la représentation cognitive de l’espace-problème, en fonction des connaissances préalables et de la découverte des affordances, permettant de générer des trajectoires-solutions créatives ; (iii) une implémentation du raisonnement par inférence au sein d’un substrat neuronalIntegrating transversal skills such as creativity, problem solving and computational thinking, into the primary and secondary curricula is a key challenge in today’s educational field. We postulate that teaching and assessing transversal competencies could benefit from a better understanding of the learners’ behaviors in specific activities that require these competencies. To this end, computational learning science is an emerging field that requires the close collaboration of computational neuroscience and educational sciences to enable the assessment of learning processes. We focus on a creative problem-solving task in which the subject is engaged into building a “vehicle” by combining modular robotic cubes. As part of an exploratory research action, we propose several approaches based on symbolic to neuro-symbolic formalisms, in order to specify such a task and model the behavior and underlying cognitive processes of a subject engaged in this task. Despite being at a very preliminary stage, such a formalization seems promising to better understand complex mechanisms involved in creative problem solving at several levels: (i) the specification of the problem and the observables of interest to collect during the task; (ii) the cognitive representation of the problem space, depending on prior knowledge and affordance discovery, allowing to generate creative solution trajectories; (iii) an implementation of reasoning mechanisms within a neuronal substrate
42
Navér, Norah. "The past, present or future? : A comparative NLP study of Naive Bayes, LSTM and BERT for classifying Swedish sentences based on their tense." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-446793.
Abstract:
Natural language processing is a field in computer science that is becoming increasingly important. One important part of NLP is the ability to sort text to the past, present or future, depending on when the event came or will come about. The objective of this thesis was to use text classification to classify Swedish sentences based on their tense, either past, present or future. Furthermore, the objective was also to compare how lemmatisation would affect the performance of the models. The problem was tackled by implementing three machine learning models on both lemmatised and not lemmatised data. The machine learning models were Naive Bayes, LSTM and BERT. The result showed that the overall performance was affected negatively when the data was lemmatised. The best performing model was BERT with an accuracy of 96.3\%. The result was useful as the best performing model had very high accuracy and performed well on newly constructed sentences.Språkteknologi är område inom datavetenskap som som har blivit allt viktigare. En viktig del av språkteknologi är förmågan att sortera texter till det förflutna, nuet eller framtiden, beroende på när en händelse skedde eller kommer att ske. Syftet med denna avhandling var att använda textklassificering för att klassificera svenska meningar baserat på deras tempus, antingen dåtid, nutid eller framtid. Vidare var syftet även att jämföra hur lemmatisering skulle påverka modellernas prestanda. Problemet hanterades genom att implementera tre maskininlärningsmodeller på både lemmatiserade och icke lemmatiserade data. Maskininlärningsmodellerna var Naive Bayes, LSTM och BERT. Resultatet var att den övergripande prestandan påverkades negativt när datan lemmatiserade. Den bäst presterande modellen var BERT med en träffsäkerhet på 96,3 \%. Resultatet var användbart eftersom den bäst presterande modellen hade mycket hög träffsäkerhet och fungerade bra på nybyggda meningar.
43
Lund, Max. "Duplicate Detection and Text Classification on Simplified Technical English." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-158714.
Abstract:
This thesis investigates the most effective way of performing classification of text labels and clustering of duplicate texts in technical documentation written in Simplified Technical English. Pre-trained language models from transformers (BERT) were tested against traditional methods such as tf-idf with cosine similarity (kNN) and SVMs on the classification task. For detecting duplicate texts, vector representations from pre-trained transformer and LSTM models were tested against tf-idf using the density-based clustering algorithms DBSCAN and HDBSCAN. The results show that traditional methods are comparable to pre-trained models for classification, and that using tf-idf vectors with a low distance threshold in DBSCAN is preferable for duplicate detection.
44
Hauschild, Jennifer M. "Fourier transform ion cyclotron resonance mass spectrometry for petroleomics." Thesis, University of Oxford, 2012. http://ora.ox.ac.uk/objects/uuid:8604a373-fb6b-4bc0-8dc1-464a191b1fac.
Abstract:
The past two decades have witnessed tremendous advances in the field of high accuracy, high mass resolution data acquisition of complex samples such as crude oils and the human proteome. With the development of Fourier transform ion cyclotron resonance mass spectrometry, the rapidly growing field of petroleomics has emerged, whose goal is to process and analyse the large volumes of complex and often poorly understood data on crude oils generated by mass spectrometry. As global oil resources deplete, oil companies are increasingly moving towards the extraction and refining of the still plentiful reserves of heavy, carbon rich and highly contaminated crude oil. It is essential that the oil industry gather the maximum possible amount of information about the crude oil prior to setting up the drilling infrastructure, in order to reduce processing costs. This project describes how machine learning can be used as a novel way to extract critical information from complex mass spectra which will aid in the processing of crude oils. The thesis discusses the experimental methods involved in acquiring high accuracy mass spectral data for a large and key industry-standard set of crude oil samples. These data are subsequently analysed to identify possible links between the raw mass spectra and certain physical properties of the oils, such as pour point and sulphur content. Methods including artificial neural networks and self organising maps are described and the use of spectral clustering and pattern recognition to classify crude oils is investigated. The main focus of the research, the creation of an original simulated annealing genetic algorithm hybrid technique (SAGA), is discussed in detail and the successes of modelling a number of different datasets using all described methods are outlined. Despite the complexity of the underlying mass spectrometry data, which reflects the considerable chemical diversity of the samples themselves, the results show that physical properties can be modelled with varying degrees of success. When modelling pour point temperatures, the artificial neural network achieved an average prediction error of less than 10% while SAGA predicted the same values with an average accuracy of more than 85%. It did not prove possible to model any of the other properties with such statistical significance; however improvements to feature extraction and pre-processing of the spectral data as well as enhancement of the modelling techniques should yield more consistent and statistically reliable results. These should in due course lead to a comprehensive model which the oil industry can use to process crude oil data using rapid and cost effective analytical methods.
45
Kanade, Varun. "Computational Questions in Evolution." Thesis, Harvard University, 2012. http://dissertations.umi.com/gsas.harvard:10556.
Abstract:
Darwin's theory (1859) proposes that evolution progresses by the survival of those individuals in the population that have greater fitness. Modern understanding of Darwinian evolution is that variation in phenotype, or functional behavior, is caused by variation in genotype, or the DNA sequence. However, a quantitative understanding of what functional behaviors may emerge through Darwinian mechanisms, within reasonable computational and information-theoretic resources, has not been established. Valiant (2006) proposed a computational model to address the question of the complexity of functions that may be evolved through Darwinian mechanisms. In Valiant's model, the goal is to evolve a representation that computes a function that is close to some ideal function under the target distribution. While this evolution model can be simulated in the statistical query learning framework of Kearns (1993), Feldman has shown that under some constraints the reverse also holds, in the sense that learning algorithms in this framework may be cast as evolutionary mechanisms in Valiant's model. In this thesis, we present three results in Valiant's computational model of evolution. The first shows that evolutionary mechanisms in this model can be made robust to gradual drift in the ideal function, and that such drift resistance is universal, in the sense that, if some concept class is evolvable when the ideal function is stationary, it is also evolvable in the setting when the ideal function drifts at some low rate. The second result shows that under certain de nitions of recombination and for certain selection mechanisms, evolution with recombination may be substantially faster. We show that in many cases polylogarithmic, rather than polynomial, generations are sufficient to evolve a concept class, whenever a suitable parallel learning algorithm exists. The third result shows that computation, and not just information, is a limiting resource for evolution. We show that when computational resources in Valiant's model are allowed to be unbounded, while requiring that the information-theoretic resources be polynomially bounded, more concept classes are evolvable. This result is based on widely believed conjectures from complexity theory.Engineering and Applied Sciences
46
Lundström, Robin. "Machine Learning for Air Flow Characterization : An application of Theory-Guided Data Science for Air Fow characterization in an Industrial Foundry." Thesis, Karlstads universitet, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-72782.
Abstract:
In industrial environments, operators are exposed to polluted air which after constant exposure can cause irreversible lethal diseases such as lung cancer. The current air monitoring techniques are carried out sparely in either a single day annually or at few measurement positions for a few days.In this thesis a theory-guided data science (TGDS) model is presented. This hybrid model combines a steady state Computational Fluid Dynamics (CFD) model with a machine learning model. Both the CFD model and the machine learning algorithm was developed in Matlab. The CFD model serves as a basis for the airflow whereas the machine learning model addresses dynamical features in the foundry. Measurements have previously been made at a foundry where five stationary sensors and one mobile robot were used for data acquisition. An Echo State Network was used as a supervised learning technique for airflow predictions at each robot measurement position and Gaussian Processes (GP) were used as a regression technique to form an Echo State Map (ESM). The stationary sensor data were used as input for the echo state network and the difference between the CFD and robot measurements were used as teacher signal which formed a dynamic correction map that was added to the steady state CFD. The proposed model utilizes the high spatio-temporal resolution of the echo state map whilst making use of the physical consistency of the CFD. The initial applications of the novel hybrid model proves that the best qualities of these two models could come together in symbiosis to give enhanced characterizations.The proposed model could have an important role for future characterization of airflow and more research on this and similar topics are encouraged to make sure we properly understand the potential of this novel model.Industriarbetare utsätts för skadliga luftburna ämnen vilket över tid leder till högre prevalens för lungsjukdomar så som kronisk obstruktiv lungsjukdom, stendammslunga och lungcancer. De nuvarande luftmätningsmetoderna genomförs årligen under korta sessioner och ofta vid få selekterade platser i industrilokalen. I denna masteruppsats presenteras en teorivägledd datavetenskapsmodell (TGDS) som kombinerar en stationär beräkningsströmningsdynamik (CFD) modell med en dynamisk maskininlärningsmodell. Både CFD-modellen och maskininlärningsalgoritmen utvecklades i Matlab. Echo State Network (ESN) användes för att träna maskininlärningsmodellen och Gaussiska Processer (GP) används som regressionsteknik för att kartlägga luftflödet över hela industrilokalen. Att kombinera ESN med GP för att uppskatta luftflöden i stålverk genomfördes första gången 2016 och denna modell benämns Echo State Map (ESM). Nätverket använder data från fem stationära sensorer och tränades på differensen mellan CFD-modellen och mätningar genomfördes med en mobil robot på olika platser i industriområdet. Maskininlärningsmodellen modellerar således de dynamiska effekterna i industrilokalen som den stationära CFD-modellen inte tar hänsyn till. Den presenterade modellen uppvisar lika hög temporal och rumslig upplösning som echo state map medan den också återger fysikalisk konsistens som CFD-modellen. De initiala applikationerna för denna model påvisar att de främsta egenskaperna hos echo state map och CFD används i symbios för att ge förbättrad karakteriseringsförmåga. Den presenterade modellen kan spela en viktig roll för framtida karakterisering av luftflöden i industrilokaler och fler studier är nödvändiga innan full förståelse av denna model uppnås.
47
Greenberg, Benjamin S. "Humanization of computational learning in strategy games." Thesis, Massachusetts Institute of Technology, 2016. http://hdl.handle.net/1721.1/106018.
Abstract:
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 89-90).
I review and describe 4 popular techniques that computers use to play strategy games: minimax, alpha-beta pruning, Monte Carlo tree search, and neural networks. I then explain why I do not believe that people use any of these techniques to play strategy games. I support this claim by creating a new strategy game, which I call Tarble, that people are able to play at a far higher level than any of the algorithms that I have described. I study how humans with various strategy game backgrounds think about and play Tarble. I then implement 3 players that each emulate how a different level of human players think about and play Tarble.
by Benjamin S. Greenberg.
M. Eng.
48
Sloan, Robert Hal. "Computational learning theory : new models and algorithms." Thesis, Massachusetts Institute of Technology, 1989. http://hdl.handle.net/1721.1/38339.
Abstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1989.Includes bibliographical references (leaves 116-120).
by Robert Hal Sloan.
Ph.D.
49
Kronbäck, Susanna, and Jevgenia Hendsel. "Algebra på gymnasiet = Svårt?! : Förekomst av felsvar och feltyper vid åk 1-gymnasieelevers beräkningar inom algebra." Thesis, Linköpings universitet, Institutionen för beteendevetenskap och lärande, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-158649.
Abstract:
Innehållet i studien handlar om att kategorisera olika typer av fel som elever i åk 1 på gymnasiet gör i algebra. Data utgörs av 80 elevprov skrivna av elever på samhällsvetenskapsprogrammet och VVS- och fastighetsprogrammet läsåret 2017/2018 och 2018/2019. Uppgifterna som eleverna har fått göra är lösa ekvationer, förenkla uttryck, räkna värdet av ett uttryck samt problemlösning. Elevernas svar har analyserats och kategoriserats i sex feltyper: 1. Förståelsefel, 2. Procedurfel, 3. Modelleringsfel eller problemlösningsfel, 4. Resonemangsfel, 5. Redovisningsfel eller kommunikationsfel, 6. Övriga fel. I resultatet preseneteras varje feltyp illustrerad med elevexempel. Med tidigre forskning som utgångspunkt identifieras och diskuteras vilka missuppfattningar och svårigheter som kan vara den bakomliggande orsaken till att eleverna gjort dessa fel. Några exempel på orsaker är att eleverna inte uppfattar variabelns (x) symboliska värde, förstår inte variablers generella beteckning (a och b), att variabeln kan representera en siffra, eleverna övergeneraliserar, förstår inte räkning med negativa tal, kan inte hantera aritmetik, förstår inte likhetstecknets betydelse, har oeffektiv resonemang (gissar, testar sig fram), samt skriver av uppgiften fel.
50
Xu, Jie S. M. Massachusetts Institute of Technology. "Learning to fly : computational controller design for hybrid UAVs with reinforcement learning." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/122772.
Abstract:
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019Cataloged from PDF version of thesis.
Includes bibliographical references (pages 51-54).
Hybrid unmanned aerial vehicles (UAV) combine advantages of multicopters and fixed-wing planes: vertical take-off, landing, and low energy use. However, hybrid UAVs are rarely used because controller design is challenging due to its complex, mixed dynamics. In this work, we propose a method to automate this design process by training a mode-free, model-agnostic neural network controller for hybrid UAVs. We present a neural network controller design with a novel error convolution input trained by reinforcement learning. Our controller exhibits two key features: First, it does not distinguish among flying modes, and the same controller structure can be used for copters with various dynamics. Second, our controller works for real models without any additional parameter tuning process, closing the gap between virtual simulation and real fabrication. We demonstrate the efficacy of the proposed controller both in simulation and in our custom-built hybrid UAVs. The experiments show that the controller is robust to exploit the complex dynamics when both rotors and wings are active in flight tests.
by Jie Xu.
S.M.
S.M. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science