Página 1 dos resultados de 17577 itens digitais encontrados em 0.030 segundos

Particle Competition and Cooperation in Networks for Semi-Supervised Learning

Breve, Fabricio; Liang, Zhao; Quiles, Marcos; Pedrycz, Witold; Liu, Jiming
Fonte: IEEE COMPUTER SOC; LOS ALAMITOS Publicador: IEEE COMPUTER SOC; LOS ALAMITOS
Tipo: Artigo de Revista Científica
ENG
Relevância na Pesquisa
46.01%
Semi-supervised learning is one of the important topics in machine learning, concerning with pattern classification where only a small subset of data is labeled. In this paper, a new network-based (or graph-based) semi-supervised classification model is proposed. It employs a combined random-greedy walk of particles, with competition and cooperation mechanisms, to propagate class labels to the whole network. Due to the competition mechanism, the proposed model has a local label spreading fashion, i.e., each particle only visits a portion of nodes potentially belonging to it, while it is not allowed to visit those nodes definitely occupied by particles of other classes. In this way, a "divide-and-conquer" effect is naturally embedded in the model. As a result, the proposed model can achieve a good classification rate while exhibiting low computational complexity order in comparison to other network-based semi-supervised algorithms. Computer simulations carried out for synthetic and real-world data sets provide a numeric quantification of the performance of the method.; State of Sao Paulo Research Foundation (FAPESP); Brazilian National Council of Technological and Scientific Development (CNPq)

Experience generalization for multi-agent reinforcement learning

Pegoraro, R.; Costa, AHR; Ribeiro, CHC; IEEE COMPUTER SOCIETY
Fonte: Institute of Electrical and Electronics Engineers (IEEE), Computer Soc Publicador: Institute of Electrical and Electronics Engineers (IEEE), Computer Soc
Tipo: Conferência ou Objeto de Conferência Formato: 233-239
ENG
Relevância na Pesquisa
46%
On-line learning methods have been applied successfully in multi-agent systems to achieve coordination among agents. Learning in multi-agent systems implies in a non-stationary scenario perceived by the agents, since the behavior of other agents may change as they simultaneously learn how to improve their actions. Non-stationary scenarios can be modeled as Markov Games, which can be solved using the Minimax-Q algorithm a combination of Q-learning (a Reinforcement Learning (RL) algorithm which directly learns an optimal control policy) and the Minimax algorithm. However, finding optimal control policies using any RL algorithm (Q-learning and Minimax-Q included) can be very time consuming. Trying to improve the learning time of Q-learning, we considered the QS-algorithm. in which a single experience can update more than a single action value by using a spreading function. In this paper, we contribute a Minimax-QS algorithm which combines the Minimax-Q algorithm and the QS-algorithm. We conduct a series of empirical evaluation of the algorithm in a simplified simulator of the soccer domain. We show that even using a very simple domain-dependent spreading function, the performance of the learning algorithm can be improved.

Practising Arithmetic Using Educational Video Games with an Interpersonal Computer

Beserra, Vagner; Nussbaum, Miguel; Zeni, Ricardo; Rodriguez, Werner; Wurman, Gabriel
Fonte: Ieee Computer Soc, Learning Technology Task Force Publicador: Ieee Computer Soc, Learning Technology Task Force
Tipo: Artigo de Revista Científica Formato: 343-358
ENG
Relevância na Pesquisa
46.07%
Studies show the positive effects that video games can have on student performance and attitude towards learning. In the past few years, strategies have been generated to optimize the use of technological resources with the aim of facilitating widespread adoption of technology in the classroom. Given its low acquisition and maintenance costs, the interpersonal computer allows individual interaction and simultaneous learning with large groups of students. The purpose of this work was to compare arithmetical knowledge acquired by third-grade students through the use of game-based activities and non-game-based activities using an interpersonal computer, with knowledge acquired through the use of traditional paper-and-pencil activities, and to analyze their impact in various socio-cultural contexts. To do this, a quasi-experimental study was conducted with 271 students in three different countries (Brazil, Chile, and Costa Rica), in both rural and urban schools. A set of educational games for practising arithmetic was developed and tested in six schools within these three countries. Results show that there were no significant differences (ANCOVA) in the learning acquired from game-based vs. non-game-based activities. However, both showed a significant difference when compared with the traditional method. Additionally...

Desenvolvimento de uma proposta didático-pedagógica para ambiente virtual de aprendizagem assistida por computador; Development of a pedagogical-didactic proposal for computer assisted learning virtual environments

Izabel Cristina de Araujo
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 23/04/2013 PT
Relevância na Pesquisa
46.1%
Essa pesquisa tem como objetivo geral desenvolver uma proposta didático-pedagógica para ambiente virtual de aprendizagem assistida por computador (AAC). Os objetivos específicos situam-se em: identificar referenciais didático-pedagógicos junto à literatura e especialistas da área, construir um quadro indicativo dos referenciais didático-pedagógicos de ambiente virtual de AAC e sistematizar os referenciais encontrados, agrupando-os em unidades de análise para composição das diretrizes norteadoras do desenvolvimento da proposta didático-pedagógica. O problema da pesquisa apresentou-se em: Como referenciais didático-pedagógicos podem nortear ações educativas em ambientes virtuais de AAC? Realizamos trabalho de campo com levantamento e revisão da literatura, anotações em diário de campo advindas da observação em campo e entrevista semi-estruturada. Tivemos a participação de 36 pesquisadores de diferentes universidades americanas, asiáticas, europeias e da Oceania. A análise dos dados de predominância qualitativa norteou as conclusões, quais sejam: que o investimento em pesquisa na área de educação com inovação tecnológica proporciona resultados práticos, impactando na formulação de políticas públicas e na formação de professores; a relevância da autoria do professor na ação educativa em ambiente virtual de AAC; o professor-autor como mediador da aprendizagem; as destrezas e os conhecimentos necessários para utilizar os materiais de ambiente de AAC se apresentam mais eficazes se autores e coautores contarem com formação básica para a utilização das ferramentas tecnológicas. Daí a importância de fazê-lo gradualmente para que sejam capazes de aumentar seu nível de autonomia frente a sua própria aprendizagem.Essa pesquisa tem como objetivo geral desenvolver uma proposta didático-pedagógica para ambiente virtual de aprendizagem assistida por computador (AAC). Os objetivos específicos situam-se em: identificar referenciais didático-pedagógicos junto à literatura e especialistas da área...

Approaches to multi-agent learning

Chang, Yu-Han, Ph. D., Massachusetts Institute of Technology
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 171 leaves; 9090627 bytes; 9097798 bytes; application/pdf; application/pdf
ENG
Relevância na Pesquisa
46.05%
Systems involving multiple autonomous entities are becoming more and more prominent. Sensor networks, teams of robotic vehicles, and software agents are just a few examples. In order to design these systems, we need methods that allow our agents to autonomously learn and adapt to the changing environments they find themselves in. This thesis explores ideas from game theory, online prediction, and reinforcement learning, tying them together to work on problems in multi-agent learning. We begin with the most basic framework for studying multi-agent learning: repeated matrix games. We quickly realize that there is no such thing as an opponent-independent, globally optimal learning algorithm. Some form of opponent assumptions must be necessary when designing multi-agent learning algorithms. We first show that we can exploit opponents that satisfy certain assumptions, and in a later chapter, we show how we can avoid being exploited ourselves. From this beginning, we branch out to study more complex sequential decision making problems in multi-agent systems, or stochastic games. We study environments in which there are large numbers of agents, and where environmental state may only be partially observable.; (cont.) In fully cooperative situations...

Multimodal dynamics : self-supervised learning in perceptual and motor systems

Coen, Michael Harlan
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 193 leaves; 13746497 bytes; 13746265 bytes; application/pdf; application/pdf
ENG
Relevância na Pesquisa
46%
This thesis presents a self-supervised framework for perceptual and motor learning based upon correlations in different sensory modalities. The brain and cognitive sciences have gathered an enormous body of neurological and phenomenological evidence in the past half century demonstrating the extraordinary degree of interaction between sensory modalities during the course of ordinary perception. We develop a framework for creating artificial perceptual systems that draws on these findings, where the primary architectural motif is the cross-modal transmission of perceptual information to enhance each sensory channel individually. We present self-supervised algorithms for learning perceptual grounding, intersensory influence, and sensorymotor coordination, which derive training signals from internal cross-modal correlations rather than from external supervision. Our goal is to create systems that develop by interacting with the world around them, inspired by development in animals. We demonstrate this framework with: (1) a system that learns the number and structure of vowels in American English by simultaneously watching and listening to someone speak. The system then cross-modally clusters the correlated auditory and visual data.; (cont.) It has no advance linguistic knowledge and receives no information outside of its sensory channels. This work is the first unsupervised acquisition of phonetic structure of which we are aware...

Learning task-specific similarity

Shakhnarovich, Gregory
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 147 p.
ENG
Relevância na Pesquisa
46.06%
The right measure of similarity between examples is important in many areas of computer science. In particular it is a critical component in example-based learning methods. Similarity is commonly defined in terms of a conventional distance function, but such a definition does not necessarily capture the inherent meaning of similarity, which tends to depend on the underlying task. We develop an algorithmic approach to learning similarity from examples of what objects are deemed similar according to the task-specific notion of similarity at hand, as well as optional negative examples. Our learning algorithm constructs, in a greedy fashion, an encoding of the data. This encoding can be seen as an embedding into a space, where a weighted Hamming distance is correlated with the unknown similarity. This allows us to predict when two previously unseen examples are similar and, importantly, to efficiently search a very large database for examples similar to a query. This approach is tested on a set of standard machine learning benchmark problems. The model of similarity learned with our algorithm provides and improvement over standard example-based classification and regression. We also apply this framework to problems in computer vision: articulated pose estimation of humans from single images...

Pearls of Wisdom : technology for intentional reflection and learning in constructionist cooperatives; Technology for intentional reflection and learning in constructionist cooperatives

Chapman, Robbin Nicole, 1958-
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 312 p.
ENG
Relevância na Pesquisa
46.16%
At the core of the constructionist learning paradigm is the idea that people learn through design experiences. However, in most settings, learners rarely revisit their work to reflect on design and learning processes. The practice of reflection is not integrated into regular community practice. That omission results in lost opportunities for deeper learning because reflection plays an important role in knowledge integration. In order to leverage the benefits of constructionist learning, learners must go beyond the activities of construction and reflect on their learning. This involves examining and gaining a deeper understanding of the how and why of their design process, including learning strategies. The conceptual framework of this dissertation, Cooperative Constructionism, establishes a design approach to reflection with a set of tools and methods that support reflection on learning. A Constructionist Cooperative is a community of learners where articulating and sharing of learning experiences is a regular practice. A goal of this dissertation is to explore the computational tools and practices that promote and support such activities. Using these tools, learners construct intentional-reflective artifacts, which embody their reflection on their design and learning experiences.; (cont.) There were two learning scaffolds developed to promote emergence of a Constructionist Cooperative. The first is a computational scaffold...

Learning probabilistic relational dynamics for multiple tasks

Deshpande, Ashwin
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 58 p.
ENG
Relevância na Pesquisa
46.05%
While large data sets have enabled machine learning algorithms to act intelligently in complex domains, standard machine learning algorithms perform poorly in situations in which little data exists for the desired target task. Transfer learning attempts to extract trends from the data of similar source tasks to enhance learning in the target task. We apply transfer learning to probabilistic rule learning to learn the dynamics of a target world. We utilize a hierarchical Bayesian framework and specify a generative model which dictates the probabilities of task data, task rulesets and a common global ruleset. Through a greedy coordinated-ascent algorithm, the source tasks contribute towards building the global ruleset which can then be used as a prior to supplement the data from the target ruleset. Simulated experimental results in a variety of blocks-world domains suggest that employing transfer learning can provide significant accuracy gains over traditional single task rule learning algorithms.; by Ashwin Deshpande.; Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2007.; Includes bibliographical references (p. 57-58).

Distributed reinforcement learning for self-reconfiguring modular robots

Varshavskaya, Paulina
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 106 p.
ENG
Relevância na Pesquisa
46.06%
In this thesis, we study distributed reinforcement learning in the context of automating the design of decentralized control for groups of cooperating, coupled robots. Specifically, we develop a framework and algorithms for automatically generating distributed controllers for self-reconfiguring modular robots using reinforcement learning. The promise of self-reconfiguring modular robots is that of robustness, adaptability and versatility. Yet most state-of-the-art distributed controllers are laboriously handcrafted and task-specific, due to the inherent complexities of distributed, local-only control. In this thesis, we propose and develop a framework for using reinforcement learning for automatic generation of such controllers. The approach is profitable because reinforcement learning methods search for good behaviors during the lifetime of the learning agent, and are therefore applicable to online adaptation as well as automatic controller design. However, we must overcome the challenges due to the fundamental partial observability inherent in a distributed system such as a self reconfiguring modular robot. We use a family of policy search methods that we adapt to our distributed problem. The outcome of a local search is always influenced by the search space dimensionality...

Vision, Learning, and Development

Brown, Christopher M. (1945 - )
Fonte: University of Rochester. Computer Science Department. Publicador: University of Rochester. Computer Science Department.
Tipo: Relatório
ENG
Relevância na Pesquisa
66.09%
It seems to be a common feeling that animals learn to see, and this feeling, together with the re-emergence of computer learning paradigms that mimic many forms of human learning, has raised hopes that learning is the key to the computer vision problem. Indeed, it seems clear that Nature does not "program" all our visual capabilities into the genome, and we certainly know that programming a computer with a closed-form solution to the vision problem is a daunting task. The aim of this informal and elementary report (basically a term paper) is to cast doubt on the idea that biological systems learn to see. The complex process of development, beginning at fertilization and ending with a mature individual, could be considered to have genetic ("nature") and learning ("nurture") processes as logical endpoints or opposite poles. This report mostly considers what goes on between those endpoints, and is meant to raise the possibility that some of the least understood processes in biology are responsible for visual capabilities.

A Comparison Between a Personalized System of Instruction (PSI) and Cooperative Learning in Teaching Computer Literacy

Martin, Nathaniel G.
Fonte: University of Rochester. Computer Science Department. Publicador: University of Rochester. Computer Science Department.
Tipo: Relatório
ENG
Relevância na Pesquisa
46.03%
A Personalized System of Instruction (PSI) is a student-paced method of teaching in which students progress by displaying mastery of written material. Cooperative Learning is a method of instruction in which students work in groups to help each other study. In the Fall of 1996, a computer literacy course in which half of the students followed a PSI curriculum and the other half followed a Cooperative Learning curriculum was offered. Data from this experiment showed several statistically significant differences between the two curricula in student satisfaction as measured by end-of-the-semester course evaluation forms. These questionnaires indicated that students felt that the PSI classes increased their knowledge at the 99\% confidence level. They also indicated that students felt that the PSI course procedures better supported course objectives, that the PSI course required more work, and that it was easier to get answers from the TAs in the PSI classes at the 95\% confidence level. The data also showed statistically significant evidence that students learned more from the PSI curriculum as measured by exams. Analysis of rosters from the programming class offered the following semester showed no statistically significant difference between the proportion of the PSI students who took the programming class and the proportion of the cooperative learning students who took the programming class.

Puzzle-based learning for engineering and computer science

Falkner, N.; Sooriamurthi, R.; Michalewicz, Z.
Fonte: IEEE Computer Soc Publicador: IEEE Computer Soc
Tipo: Artigo de Revista Científica
Publicado em //2010 EN
Relevância na Pesquisa
46.03%
To attract, motivate, and retain students and increase their mathematical awareness and problem-solving skills, universities are introducing courses or seminars that explore puzzle-based learning. We introduce and define this learning approach with a sample syllabus and course material, describe course variations, and highlight early student feedback.; Nickolas Falkner, Raja Sooriamurthi and Zbigniew Michalewicz

Development of intelligent computer-assisted instruction systems to facilitate reading skills of learning-disabled children

Anderson, Patricia M.
Fonte: Monterey, California. Naval Postgraduate School Publicador: Monterey, California. Naval Postgraduate School
Tipo: Tese de Doutorado Formato: 90 p.
EN_US
Relevância na Pesquisa
46.12%
Approved for public release; distribution is unlimited; The purpose of this thesis is to develop a high-level model to create self-adapting software which teaches learning-disabled (LD) children to read. This approach identifies and discusses the fundamental concepts of learning, motivation, learning disabilities, the Theory of Multiple Intelligences, computer games, and intelligent computer-aided learning (ICAL). These concepts are then integrated into the design of a model that manipulates these concepts to teach reading skills. The result of this effort is CAPER (Computer-Assisted Personal Education Resource). It is model of a system that will: (a) identify the individual's dominant learning styles, (b) tailor the instruction and presentation to those styles, and (C) present the lessons in an interactive game-like style will retain the child's interest and enhance the learning process.; http://archive.org/details/developmentofint00ande; Captain, United States Army

A basic guide to open educational resources (OER)

Kanwar, Asha; Uvalić-Trumbić, Stamenka; Butcher, Neil
Fonte: Vancouver : Commonwealth of Learning ; Paris : UNESCO Publicador: Vancouver : Commonwealth of Learning ; Paris : UNESCO
Tipo: Livro Formato: application/pdf
ENG
Relevância na Pesquisa
46.06%
133 p. : ill.; Libro Electrónico; This Guide comprises three sections. The first – a summary of the key issues – is presented in the form of a set of ‘Frequently Asked Questions’. Its purpose is to provide readers with a quick and user-friendly introduction to Open Educational Resources (OER) and some of the key issues to think about when exploring how to use OER most effectively. The second section is a more comprehensive analysis of these issues, presented in the form of a traditional research paper. For those who have a deeper interest in OER, this section will assist with making the case for OER more substantively. The third section is a set of appendices, containing more detailed information about specific areas of relevance to OER. These are aimed at people who are looking for substantive information regarding a specific area of interest; Contents Acknowledgements 1 Overview of the Guide 3 A Basic Guide to Open Educational Resources: Frequently asked questions 5 What are Open Educational Resources (OER)? 5 Is OER the same as e-learning? 5 Is OER the same as open learning/open education? 6 Is OER related to the concept of resource-based learning? 7 How open is an open licence? 8 What is the difference between OER and open access publishing? 9 Shouldn’t I worry about ‘giving away’ my intellectual property? 9 Who will guarantee the quality of OER? 12 How can education benefit by harnessing OER? 13 Is OER really free? 14 Does use of OER preclude use of commercial content? 16 What policy changes are needed for institutions to make more effective use of OER? 16 What are the best ways to build capacity in OER? 17 Where do I find OER? 18 How can I share my OER with others? 19 How much can I change OER for my own purposes? 20 Making the Case for Open Educational Resources 23 Introduction 23 Defining the concept 24 The implications for educational planners and decision-makers 39 Conclusion 44 References 45 Appendix One: Overview of Open Licences 47 Introduction 47 Creative Commons Licences 48 Appendix References 52 Appendix Two: The Components of a Well-Functioning Distance Education System 53 The Components 53 The Rationale for Use of Distance Education Methods 55 Appendix Three: Technology Applications 57 iii Appendix Four: Open Source Software Applications in Education 61 References 64 Appendix Five: Mapping the OER Terrain Online 65 Introduction 65 OCW OER Repositories 65 University OCW Initiatives 70 Subject-Specific OCW OER 74 Content Creation Initiatives 78 Open Schooling Initiatives 81 OCW OER Search 84 Conclusion 85 Appendix Six: A Catalogue of OER-Related Websites 87 OCW OER Repositories 88 Open Schooling Initiatives 92 OCW OER Search 93 University OCW Initiatives 95 Subject-Specific OCW-OER 104 OER Tools 109 Other OER Sources 113 Appendix Seven: Some OER Policy Issues in Distance Education 115 Appendix Eight: OER Policy Review Process 123 Appendix Nine: Skills Requirements for Work in Open Educational Resources 131

Learning continuous models for estimating intrinsic component images

Tappen, Marshall Friend, 1976-
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 144 leaves
ENG
Relevância na Pesquisa
46.01%
The goal of computer vision is to use an image to recover the characteristics of a scene, such as its shape or illumination. This is difficult because an image is the mixture of multiple characteristics. For example, an edge in an image could be caused by either an edge on a surface or a change in the surface's color. Distinguishing the effects of different scene characteristics is an important step towards high-level analysis of an image. This thesis describes how to use machine learning to build a system that recovers different characteristics of the scene from a single, gray-scale image of the scene. The goal of the system is to use the observed image to recover images, referred to as Intrinsic Component Images, that represent the scene's characteristics. The development of the system is focused on estimating two important characteristics of a scene, its shading and reflectance, from a single image. From the observed image, the system estimates a shading image, which captures the interaction of the illumination and shape of the scene pictured, and an albedo image, which represents how the surfaces in the image reflect light. Measured both qualitatively and quantitatively, this system produces state-of-the-art estimates of shading and albedo images.; (cont.) This system is also flexible enough to be used for the separate problem of removing noise from an image. Building this system requires algorithms for continuous regression and learning the parameters of a Conditionally Gaussian Markov Random Field. Unlike previous work...

Dealers, insiders and bandits : learning and its effects on market outcomes

Das, Sanmay, 1979-
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 149 p.
ENG
Relevância na Pesquisa
46.08%
This thesis seeks to contribute to the understanding of markets populated by boundedly rational agents who learn from experience. Bounded rationality and learning have both been the focus of much research in computer science, economics and finance theory. However, we are at a critical stage in defining the direction of future research in these areas. It is now clear that realistic learning problems faced by agents in market environments are often too hard to solve in a classically rational fashion. At the same time, the greatly increased computational power available today allows us to develop and analyze richer market models and to evaluate different learning procedures and algorithms within these models. The danger is that the ease with which complex markets can be simulated could lead to a plethora of models that attempt to explain every known fact about different markets. The first two chapters of this thesis define a principled approach to studying learning in rich models of market environments, and the rest of the thesis provides a proof of concept by demonstrating the applicability of this approach in modeling settings drawn from two different broad domains, financial market microstructure and search theory. In the domain of market microstructure...

Learning with online constraints : shifting concepts and active learning

Monteleoni, Claire E. (Claire Elizabeth), 1975-
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 102 p.
ENG
Relevância na Pesquisa
46.09%
Many practical problems such as forecasting, real-time decision making, streaming data applications, and resource-constrained learning, can be modeled as learning with online constraints. This thesis is concerned with analyzing and designing algorithms for learning under the following online constraints: i) The algorithm has only sequential, or one-at-time, access to data. ii) The time and space complexity of the algorithm must not scale with the number of observations. We analyze learning with online constraints in a variety of settings, including active learning. The active learning model is applicable to any domain in which unlabeled data is easy to come by and there exists a (potentially difficult or expensive) mechanism by which to attain labels. First, we analyze a supervised learning framework in which no statistical assumptions are made about the sequence of observations, and algorithms are evaluated based on their regret, i.e. their relative prediction loss with respect to the hindsight-optimal algorithm in a comparator class. We derive a, lower bound on regret for a class of online learning algorithms designed to track shifting concepts in this framework. We apply an algorithm we provided in previous work, that avoids this lower bound...

Cognitive-developmental learning for a humanoid robot : a caregiver's gift

Arsenio, Artur Miguel Do Amaral, 1972-
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: Tese de Doutorado Formato: 341 p.; 16402738 bytes; 16449178 bytes; application/pdf; application/pdf
EN_US
Relevância na Pesquisa
46.01%
(cont.) which are then applied to developmentally acquire new object representations. The humanoid robot therefore sees the world through the caregiver's eyes. Building an artificial humanoid robot's brain, even at an infant's cognitive level, has been a long quest which still lies only in the realm of our imagination. Our efforts towards such a dimly imaginable task are developed according to two alternate and complementary views: cognitive and developmental.; The goal of this work is to build a cognitive system for the humanoid robot, Cog, that exploits human caregivers as catalysts to perceive and learn about actions, objects, scenes, people, and the robot itself. This thesis addresses a broad spectrum of machine learning problems across several categorization levels. Actions by embodied agents are used to automatically generate training data for the learning mechanisms, so that the robot develops categorization autonomously. Taking inspiration from the human brain, a framework of algorithms and methodologies was implemented to emulate different cognitive capabilities on the humanoid robot Cog. This framework is effectively applied to a collection of AI, computer vision, and signal processing problems. Cognitive capabilities of the humanoid robot are developmentally created...

Learning Sequences

Eppstein, David
Fonte: Universidade Cornell Publicador: Universidade Cornell
Tipo: Artigo de Revista Científica
Publicado em 27/03/2008
Relevância na Pesquisa
46.02%
We describe the algorithms used by the ALEKS computer learning system for manipulating combinatorial descriptions of human learners' states of knowledge, generating all states that are possible according to a description of a learning space in terms of a partial order, and using Bayesian statistics to determine the most likely state of a student. As we describe, a representation of a knowledge space using learning sequences (basic words of an antimatroid) allows more general learning spaces to be implemented with similar algorithmic complexity. We show how to define a learning space from a set of learning sequences, find a set of learning sequences that concisely represents a given learning space, generate all states of a learning space represented in this way, and integrate this state generation procedure into a knowledge assessment algorithm. We also describe some related theoretical results concerning projections of learning spaces, decomposition and dimension of learning spaces, and algebraic representation of learning spaces.; Comment: 37 pages, 15 figures. To appear as a chapter of J.-Cl. Falmagne, C. Doble, and X. Hu, eds., Knowledge Spaces: Applications in Education