Results 1 - 10 of 1,308

Manifold regularization: A geometric framework for learning from labeled and unlabeled examples

by Mikhail Belkin, Partha Niyogi, Vikas Sindhwani - JOURNAL OF MACHINE LEARNING RESEARCH , 2006
"... We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised framework that incorporates labeled and unlabeled data in a general-purpose learner. Some transductive graph learning al ..."
Abstract - Cited by 578 (16 self) - Add to MetaCart
algorithms and standard methods including Support Vector Machines and Regularized Least Squares can be obtained as special cases. We utilize properties of Reproducing Kernel Hilbert spaces to prove new Representer theorems that provide theoretical basis for the algorithms. As a result (in contrast to purely

Utility Representation of an Incomplete Preference Relation

by Efe A. Ok , 2000
"... We consider the problem of representing a (possibly) incomplete preference relation by means of a vector-valued utility function. Continuous and semicontinuous representation results are reported in the case of preference relations that are, in a sense, not “too incomplete.” These results generalize ..."
Abstract - Cited by 64 (6 self) - Add to MetaCart
generalize some of the classical utility representation theorems of the theory of individual choice, and paves the way towards developing a consumer theory that realistically allows individuals to exhibit some “indecisiveness” on occasion.

A Generalized Representer Theorem

by Bernhard Schölkopf, Ralf Herbrich, Alex J. Smola - In Proceedings of the Annual Conference on Computational Learning Theory , 2001
"... Wahba's classical representer theorem states that the solutions of certain risk minimization problems involving an empirical risk term and a quadratic regularizer can be written as expansions in terms of the training examples. We generalize the theorem to a larger class of regularizers and ..."
Abstract - Cited by 222 (17 self) - Add to MetaCart
Wahba's classical representer theorem states that the solutions of certain risk minimization problems involving an empirical risk term and a quadratic regularizer can be written as expansions in terms of the training examples. We generalize the theorem to a larger class of regularizers

A Linear Logical Framework

by Iliano Cervesato, Frank Pfenning , 1996
"... We present the linear type theory LLF as the forAppeared in the proceedings of the Eleventh Annual IEEE Symposium on Logic in Computer Science --- LICS'96 (E. Clarke editor), pp. 264--275, New Brunswick, NJ, July 27--30 1996. mal basis for a conservative extension of the LF logical framework. ..."
Abstract - Cited by 234 (48 self) - Add to MetaCart
semantics, and a proof of type preservation. Another example is the encoding of a sequent calculus for classical linear logic and its cut elimination theorem. LLF can also be given an operational interpretation as a logic programming language under which the representations above can be used for type

A Theory of Networks for Approximation and Learning

by Tomaso Poggio, Federico Girosi - Laboratory, Massachusetts Institute of Technology , 1989
"... Learning an input-output mapping from a set of examples, of the type that many neural networks have been constructed to perform, can be regarded as synthesizing an approximation of a multi-dimensional function, that is solving the problem of hypersurface reconstruction. From this point of view, t ..."
Abstract - Cited by 235 (24 self) - Add to MetaCart
, this form of learning is closely related to classical approximation techniques, such as generalized splines and regularization theory. This paper considers the problems of an exact representation and, in more detail, of the approximation of linear and nonlinear mappings in terms of simpler functions

Non-Classical Expected Utility Theory ∗

by V. I. Danilov, A. Lambert-mogiliansky , 2006
"... In this paper we extend Savage’s theory of decision-making under uncertainty from a classical environment into a non-classical one. We formulate the corresponding axioms and provide representation theorems for qualitative measures and expected utility. 1 ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
In this paper we extend Savage’s theory of decision-making under uncertainty from a classical environment into a non-classical one. We formulate the corresponding axioms and provide representation theorems for qualitative measures and expected utility. 1

Representation Theorems and Theorem Proving in Non-Classical Logics

by Viorica Sofronie-stokkermans - In Proceedings of the 29th IEEE International Symposium on Multiple-Valued Logic. IEEE Computer Sociaty , 1999
"... In this paper we present a method for automated theorem proving in non-classical logics having as algebraic models bounded distributive lattices with certain types of operators. The idea is to use a Priestley-style representation for distributive lattices with operators in order to define a class of ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
In this paper we present a method for automated theorem proving in non-classical logics having as algebraic models bounded distributive lattices with certain types of operators. The idea is to use a Priestley-style representation for distributive lattices with operators in order to define a class

P-CLASSIC: A tractable probabilistic description logic

by Daphne Koller, Alon Levy, Avi Pfeffer - In Proceedings of AAAI-97 , 1997
"... Knowledge representation languages invariably reflect a trade-off between expressivity and tractability. Evidence suggests that the compromise chosen by description logics is a particularly successful one. However, description logic (as for all variants of first-order logic) is severely limited in i ..."
Abstract - Cited by 119 (4 self) - Add to MetaCart
in its ability to express uncertainty. In this paper, we present P-CLASSIC, a probabilistic version of the description logic CLASSIC. In addition to terminological knowledge, the language utilizes Bayesian networks to express uncertainty about the basic properties of an individual, the number of fillers

Behavioral theories and the neurophysiology of reward,

by Wolfram Schultz - Annu. Rev. Psychol. , 2006
"... ■ Abstract The functions of rewards are based primarily on their effects on behavior and are less directly governed by the physics and chemistry of input events as in sensory systems. Therefore, the investigation of neural mechanisms underlying reward functions requires behavioral theories that can ..."
Abstract - Cited by 187 (0 self) - Add to MetaCart
the frequency of the behavior that results in reward. In Pavlovian, or classical, conditioning, the outcome follows the conditioned stimulus (CS) irrespective of any behavioral reaction, and repeated pairing of stimuli with outcomes leads to a representation of the outcome that is evoked by the stimulus

Representation Theorems and the Semantics of Non-Classical Logics , and Applications to Automated Theorem Proving

by Viorica Sofronie-stokkermans , 2002
"... We give a uniform presentation of representation and decidability results related to the Kripke-style semantics of several nonclassical logics. We show that a general representation theorem (which has as particular instances the representation theorems as algebras of sets for Boolean algebras, d ..."
Abstract - Cited by 8 (2 self) - Add to MetaCart
We give a uniform presentation of representation and decidability results related to the Kripke-style semantics of several nonclassical logics. We show that a general representation theorem (which has as particular instances the representation theorems as algebras of sets for Boolean algebras
Results 1 - 10 of 1,308