
	Where results make sense

Topic: Computational learning theory

Related Topics

Vapnik Chervonenkis theory

Reinforcement learning

Support vector machine

Neural networks

Data clustering

Artificial intelligence

Codimension

Neuroevolution

Data compression

Vector space

Affine transformation

Hyperplane

In the News (Mon 16 Nov 09)

Northern Trust

Marvin Harrison

Peter Chernin

Gary Locke

Match Play

Penelope Cruz

Mickey Rourke

AR Rahman

Danny Boyle

Hugh Jackman

	Computational learning theory - Wikipedia, the free encyclopedia
		In statistics, computational learning theory is a mathematical field related to the analysis of machine learning algorithms.
		Because the training set is finite and the future is uncertain, learning theory usually does not yield absolute guarantees of performance of the algorithms.
		In computational learning theory, a computation is considered feasible if it can be done in polynomial time.
	en.wikipedia.org /wiki/Computational_learning_theory (522 words)

	COLT: Computational Learning Theory
		Computational Learning Theory (COLT) is a reasearch field devoted to studying the design and analysis of algorithms for making predictions about the future based on past experiences.
		As a field with roots in theoretical computer science, COLT is largely concerned with computational and data efficiency.
		The annual Conference on Computational Learning Theory began in 1988; the European Conference on Computational Learning Theory and the Workshop on Algorithmic Learning Theory were formed soon after.
	www.learningtheory.org (163 words)

	Formal Learning Theory
		Formal learning theory is the mathematical embodiment of a normative epistemology.
		Learning theory is pure normative a priori epistemology, in the sense that it deals with standards for assessing methods in possible settings of inquiry.
		Learning theorists have shown that whenever there is a reliable method for investigating an empirical question, there is one that proceeds via minimal changes (as defined by the AGM postulates).
	plato.stanford.edu /entries/learning-formal (7031 words)

	Encyclopedia: Computational learning theory
		Bayesianism is the philosophical tenet that the mathematical theory of probability applies to the degree of plausibility of a statement.
		Probably approximately correct learning (PAC learning) is a framework of learning that was proposed by Leslie Valiant in his paper A theory of the learnable.
		Parameters of the learning algorithm may be adjusted by optimizing performance on a subset (called a validation set) of the training set, or via cross-validation.
	www.nationmaster.com /encyclopedia/Computational-learning-theory (1182 words)

	Learning theory - Wikipedia, the free encyclopedia
		In education and psychology, learning theory is a theory about the process of how humans learn.
		In philosophy, formal learning theory is a theory about the proper behavior of individuals learning about their environment
		In statistics, computational learning theory is a mathematical theory to analyze machine learning algorithms.
	en.wikipedia.org /wiki/Learning_theory (147 words)

	Computational complexity theory (Site not responding. Last check: 2007-10-13)
		Complexity theory is part of the theory of computation dealing with the resources required during computation to solve a given problem.
		Complexity theory differs from computability theory, which deals with whether a problem can be solved at all, regardless of the resources required.
		After the theory explaining which problems can be solved and which cannot be, it was natural to ask about the relative computational difficulty of computable functions.
	hallencyclopedia.com /Computational_complexity_theory (1159 words)

	The Computational Theory of Mind
		A second important issue in nineteenth and early twentieth century mathematics was one of delimiting the class of functions that are "computable" in the technical sense of being decidable or evaluable by the application of a rote procedure or algorithm.
		Turing's proposal was that the class of computable functions was equivalent to the class of functions that could be evaluated in a finite number of steps by a machine of the design he proposed.
		Regardless of one's outlook on the general prospects of causal theories of meaning, a sense of "meaning" that is cashed out in terms of causal covariance or causal etiology cannot be equivalent to either speaker meaning or conventional interpretability.
	plato.stanford.edu /entries/computational-mind (6686 words)

	Computational Learning Theory and Natural Learning Systems - Vol. II - The MIT Press (Site not responding. Last check: 2007-10-13)
		While the first volume provided a forum for building a science of computational learning across fields, this volume attempts to define plausible areas of joint research: the contributions are concerned with finding constraints for theory while at the same time interpreting theoretic results in the context of experiments with actual learning systems.
		Computational learning theory, neural networks, and AI machine learning appear to be disparate fields; in fact they have the same goal: to build a machine or program that can learn from its environment.
		The first section provides theoretical explanations for the learning systems addressed, the second section focuses on issues in model selection and inductive bias, the third section presents new learning algorithms, the fourth section explores the dynamics of learning in feedforward neural networks, and the final section focuses on the application of learning algorithms.
	mitpress.mit.edu /catalog/item?ttype=2&tid=5633 (295 words)

	COMS E6998 Advanced Topics in Computational Learning Theory, Spring 2005
		COMS E6998 is an advanced graduate course on efficient algorithms in computational learning theory.
		The course can be used as a theory elective for the Ph.D. program in computer science, or as an track elective course for MS students in the "Foundations of Computer Science" track or the "Machine Learning" track.
		COMS 4252 (Computational Learning Theory), or its prior incarnation as COMS 4995, is ideal preparation.
	www1.cs.columbia.edu /~rocco/6998 (1202 words)

	Computational Learning Theory (Site not responding. Last check: 2007-10-13)
		The learning algorithm may query an oracle for the value of the formula f on a particular variable assignment x.
		We say that the learning algorithm is efficient if the unknown target formula f can be exactly learned (identified) in polynomial time in the length of its input and output.
		For example, the class of monotone Boolean functions is often representative of real-life phenomena and has been studied in the context of learning in such fields as medical diagnosis, manufacturing and reliability analysis, as well as signal processing.
	www2.mdanderson.org /app/ilya/LEARN.htm (698 words)

	Communications Theory, Signal Processing, and computational Learning Theory
		Current research is concerned with the characterization of the basic capabilities of such networks, development and evaluation of adaptive alg orithms or learning techniques for network parameters, extensions of network structures for enhanced performance in specific situations such as those involving complex data, and considerations of efficient implementation.
		The complexity of learning has attracted substantial interest in recent years and a divers set of questions in this burgeoning area are being investigated ranging from an information-theoretic characterization of the learning process to the development of algorithms for learning in particular structures.
		While many learning procedures are provably efficient in the limit of an infinite number of examples, there i s a relative paucity of results on their finite sample performance.
	www.seas.upenn.edu /~kassam/field.comm.html (694 words)

	Computational Learning Theory: PAC Learning
		PAC Learning deals with the question of how to choose the size of the training set, if we want to have confidence delta that the learned concept will have an error that is bound by epsilon.
		We compute first the probability that a literal z is deleted from h because of one specific positive example.
		In our context, "Occam Learning" implies that when learning concepts we should give preference to hypotheses that are simple, in the sense of being short ("short" is defined as a function of the shortest possible description for the concept and the size of the training set).
	www.cis.temple.edu /~ingargio/cis587/readings/pac.html (1844 words)

	Computational Learning Theory (ResearchIndex) (Site not responding. Last check: 2007-10-13)
		Abstract: Introduction Since the late fifties, computer scientists (particularly those working in the area of artificial intelligence) have been trying to understand how to construct computer programs that perform tasks we normally think of as requiring human intelligence, and which can improve their performance over time by modifying their behavior in response to experience.
		521 A theory of the learnable (context) - Valiant - 1984
		Learning of Context-Free Languages: A Survey of the Literature - Lee (1996)
	citeseer.ist.psu.edu /275016.html (675 words)

	Comp 150-CLT: Computational Learning Theory
		This course is concerned with formal models of machine learning, the computational problems associated with such models, their feasibility and complexity, and efficient algorithms for them.
		Several aspects and models will be studied including: learning as on-line prediction, learning in probabilistic settings, learning from noisy (corrupted) data, and learning by asking questions.
		A decision-theoretic generalization of on-line learning and an application to boosting.
	www.cs.tufts.edu /comp/150CLT (642 words)

	Avrim Blum's publications
		Learning from Labeled and Unlabeled Data using Graph Mincuts.
		Proceedings of the 12th Annual Conference on Computational Learning Theory (COLT '99), pp.
		Learning an Intersection of a Constant Number of Halfspaces over a Uniform Distribution.
	www.cs.cmu.edu /~avrim/Papers/pubs_old.html (1178 words)

	COMS 70303: Computational Learning Theory (Site not responding. Last check: 2007-10-13)
		The aim of this unit is to equip students with the knowledge and skills necessary to formally analyse learning algorithms and determine the assumptions under which a particular class of tasks is learnable.
		This unit presents the basics of computational learning theory, with an emphasis on PAC-learnability.
		With this unit, students are encouraged to place the results of empirical studies in their proper context and to recognise the limitations of the models and algorithms they may use.
	www.cs.bris.ac.uk /Tools/Local/Handbook9899/Units/COMS70303.html (139 words)

	Computational Learning Theory - Cambridge University Press (Site not responding. Last check: 2007-10-13)
		Computational learning theory is a subject which has been advancing rapidly in the last few years.
		The authors concentrate on the probably approximately correct model of learning, and gradually develop the ideas of efficiency considerations.
		It will therefore form an introduction to the theory of computational learning, suitable for a broad spectrum of graduate students from theoretical computer science and mathematics.
	www.cup.cam.ac.uk /catalogue/print.asp?isbn=0521599229&print=y (148 words)

	References for Methods of Computational Group Theory
		The Computer Algebra Handbook [GKW03] aims to provide an overview of the full field of computer algebra by individual articles written by different authors in the style of an encyclopedia.
		There are surveys on different areas and aspects as well as descriptions of program systems, a bibliography with over 2100 entries, and pointers to many conferences since 1979 and their proceedings.
		The authoritative text on the subject of computing methods for fp groups is the book [Si94] by Charles C. Sims.
	www.gap-system.org /Doc/references.html (535 words)

	Amazon.com: Computational Learning Theory and Natural Learning Systems, Vol. IV: Making Learning Systems Practical: ... (Site not responding. Last check: 2007-10-13)
		This is the fourth and final volume of papers from a series of workshops called "Computational Learning Theory and 'Natural' Learning Systems." The purpose of the workshops was to explore the emerging intersection of theoretical learning research and natural learning systems.
		The workshops drew researchers from three historically distinct styles of learning research: computational learning theory, neural networks, and machine learning (a subfield of AI).
		The task of inductive learning from examples is to find an approximate definition for an unknown function f(x), given training examples of the form xi, f(xi).
	www.amazon.com /exec/obidos/tg/detail/-/0262571188?v=glance (708 words)

	Amazon.ca: Computational Learning Theory and Natural Learning Systems - Vol. III : Selecting Good Models: Books (Site not responding. Last check: 2007-10-13)
		This is the third in a series of edited volumes exploring the evolving landscape of learning systems research which spans theory and experiment, symbols and signals.
		The nineteen contributions cover learning theory, empirical comparisons of learning algorithms, the use of prior knowledge, probabilistic concepts, and the effect of variations over time in the concepts and feedback from the environment.
		These volumes present research that should be of interest to practitioners of the various subdisciplines of machine learning, addressing questions that are of interest across the range of machine learning approaches, comparing various approaches on specific problems and expanding the theory to cover more realistic cases.
	www.amazon.ca /exec/obidos/ASIN/0262660962 (392 words)

	Home Page for Professor Michael Kearns, University of Pennsylvania
		The Computational Complexity of Machine Learning This revision of my doctoral dissertation was published by the MIT Press as part of the ACM Distinguished Dissertation Series; the link above is to the MIT Press order form for the book.
		Proceedings of the 25th ACM Symposium on the Theory of Computing, pp.
		Proceedings of the 19th ACM Symposium on the Theory of Computing, pp.
	www.cis.upenn.edu /~mkearns (2617 words)

	IBM Research \| Israel \| Seminars \| A Biased Introduction to Computational Learning Theory (Site not responding. Last check: 2007-10-13)
		It is a relatively young field that employ tools ranging from statistics to computational complexity and geometry in an attempt to provide theoretical foundations to some important practical AI'ish issues.
		I shall do so by focusing on a specific subfield - Agnostic Learning - a learning paradigm that is central to both the theory and applications of machine learning.
		I shall talk about common learning algorithms, mention some practical applications, and finally talk about recent results showing the inherent computational hardness of some of the basic algorithmic tasks that arise in this context.
	domino.research.ibm.com /comm/wwwr_seminar.nsf/pages/sem_abstract_57.html (160 words)

	An Introduction to Computational Learning Theory - The MIT Press
		Emphasizing issues of computational efficiency, Michael Kearns and Umesh Vazirani introduce a number of central topics in computational learning theory for researchers and students in artificial intelligence, neural networks, theoretical computer science, and statistics.
		Computational learning theory is a new and rapidly expanding area of research that examines formal models of induction with the goals of discovering the common methods underlying efficient learning algorithms and identifying the computational impediments to learning.
		Michael J. Kearns is Professor of Computer and Information Science at the University of Pennsylvania.
	mitpress.mit.edu /catalog/item?ttype=2&tid=7334 (158 words)

	Computational Learning Group (Site not responding. Last check: 2007-10-13)
		Computational learning theory (COLT) research has made significant progress in our understanding of concept learning from sampled labeled instances.
		Active Learning 1: Learning from Data with Unspecified Attribute Values: Almost all work in COLT assumes that the attribute values of the instances are totally specified.
		Bylander, Polynomial learnability of linear threshold approximations, Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, pp.
	www.cs.utsa.edu /~kwek/CLG (1714 words)

	John Case's COLT Page
		Computational Learning Theory (COLT) is a branch of theoretical computer science which mathematically studies the power of computer programs to learn (algorithmic) rules for predicting things such as membership in a concept or, as in the first example above, rules for how to generate a sequence.
		Besides the intrinsic scientific and philosophical interest, the expected primary applications of COLT are to construction of intelligent technology, especially technology which learns, and to cognitive psychology, including understanding human language acquisition (brief postscript bibliography available) and scientific inductive inference (brief postscript bibliography available).
		Wiehagen), Proceedings of the Fourteenth Annual Conference on Computational Learning Theory (COLT'01) and The Fifth European Conference on Computational Learning Theory (EuroCOLT'01), to be held in Amsterdam, The Netherlands, July, 2001, to appear, 2001.
	www.cis.udel.edu /~case/colt.html (1528 words)

	Computational Learning Theory (ResearchIndex) (Site not responding. Last check: 2007-10-13)
		Abstract: estions in Computational Learning Theory (COLT) with the goal of strengthening two of the laboratory's core competency areas (theory modeling and high performance computing, and analysis and assessment), with relevance to others as well (see http://www.lanl.gov/ worldview/science/core/).
		9 Elements of a Theory of Computer Simulation I: Sequential CA..
		8 Elements of a Theory of Computer Simulation III: Equivalence..
	citeseer.ist.psu.edu /398844.html (452 words)

	Computational Learning Theory
		This learning theory has been used as a basis for analyzing the properties of learning algorithms.
		An agnostic learner does not assume that the target concept is in H and can learn a hypothesis with nonzero training error.
		Given an infinite hypothesis H for learning a concept, the learning system which learns a set of m random instances is probably approximately correct with probability delta and accuracy epsilon if
	www.cise.ufl.edu /~fu/Lecture/Learn/theory-fu.html (471 words)

	Computational Learning Theory
		Inductive synthesis and computational learning theory are research direction where Institute has long-standing traditions.
		In the seventies inductive synthesis was studied on the level of recursive function theory (J.Barzdins, R.Freivalds, K.Podnieks).
		At the beginning of 1990s the models of inductive synthesis based on abstract data types and term rewriting systems were studied, computer experiments were performed and a new efficient inductive synthesis algorithms were found (G.Barzdins).
	www.lumii.lv /cs/clt.htm (277 words)

Try your search on: Qwika (all wikis)