Results 1  10
of
4,539
Hypothesis Spaces for Learning
"... Abstract. In this paper we survey some results in inductive inference showing how learnability of a class of languages may depend on hypothesis space chosen. We also discuss results which consider how learnability is effected if one requires learning with respect to every suitable hypothesis space. ..."
Abstract
 Add to MetaCart
Abstract. In this paper we survey some results in inductive inference showing how learnability of a class of languages may depend on hypothesis space chosen. We also discuss results which consider how learnability is effected if one requires learning with respect to every suitable hypothesis space
Aggregation Operators and Hypothesis Space Reductions
 in Speech Recognition, Text, Speech and Dialogue ’04
, 2004
"... Abstract. In this paper we deal with the heuristic exploration of general hypothesis spaces arising both in the HMM and segmentbased approaches of speech recognition. The generated hypothesis space is a tree where we assign costs to its nodes. The tree and the costs are both generated in a topdown ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
Abstract. In this paper we deal with the heuristic exploration of general hypothesis spaces arising both in the HMM and segmentbased approaches of speech recognition. The generated hypothesis space is a tree where we assign costs to its nodes. The tree and the costs are both generated in a top
Hypothesis Space Checking in Intuitive Reasoning
"... The process of generating a new hypothesis often begins with the recognition that all of the hypotheses currently under consideration are wrong. While this sort of falsification is straightforward when the observations are incompatible with each of the hypotheses, an interesting situation arises whe ..."
Abstract
 Add to MetaCart
inference that account for hypothesis comparison but do not explain how a reasoner might decide that the hypothesis space needs to be expanded.
Control Structures in Hypothesis Spaces: The Influence on Learning
"... . In any learnability setting, hypotheses are conjectured from some hypothesis space. Studied herein are the effects on learnability of the presence or absence of certain control structures in the hypothesis space. First presented are control structure characterizations of some rather specific but ..."
Abstract

Cited by 4 (2 self)
 Add to MetaCart
. In any learnability setting, hypotheses are conjectured from some hypothesis space. Studied herein are the effects on learnability of the presence or absence of certain control structures in the hypothesis space. First presented are control structure characterizations of some rather specific
An invariance property of predictors in kernelinduced hypothesis spaces
 Neural Comput
, 2006
"... We consider kernel based learning methods for regression and analyze what happens to the risk minimizer when new variables, statistically independent of input and target variables, are added to the set of input variables; this problem arises, for example, in the detection of causality relations betw ..."
Abstract

Cited by 6 (1 self)
 Add to MetaCart
between two time series. We find that the risk minimizer remains unchanged if we constrain the risk minimization to hypothesis spaces induced by suitable kernel functions. We show that not all kernel induced hypothesis spaces enjoy this property. We present sufficient conditions ensuring that the risk
Sparse Regression Ensembles in Infinite and Finite Hypothesis Spaces
, 2000
"... We examine methods for constructing regression ensembles based on a linear program (LP). The ensemble regression function consists of linear combina tions of base hypotheses generated by some boostingtype base learning algorithm. Unlike the classification case, for regression the set of possible h ..."
Abstract

Cited by 23 (8 self)
 Add to MetaCart
hypotheses producible by the base learning algorithm may be infinite. We explicitly tackle the issue of how to define and solve ensemble regression when the hypothesis space is infinite. Our approach is based on a semiinfinite linear program that has an infinite number of constraints and a finite number
Language Series Revisited: The Complexity of Hypothesis Spaces in ILP
 In Proceedings of the 8th European Conference on Machine Learning
, 1995
"... . Restrictions on the number and depth of existential variables as defined in the language series of Clint [Rae92] are widely used in ILP and expected to produce a considerable reduction in the size of the hypothesis space. In this paper we show that this is generally not the case. The lower bounds ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
. Restrictions on the number and depth of existential variables as defined in the language series of Clint [Rae92] are widely used in ILP and expected to produce a considerable reduction in the size of the hypothesis space. In this paper we show that this is generally not the case. The lower bounds
Control Structures in Hypothesis Spaces: The Influence on Learning
"... In any learnability setting, hypotheses are conjectured from some hypothesis space. Studied herein are the influence on learnability of the presence or absence of certain control structures in the hypothesis space. First presented are control structure characterizations of some rather specific but i ..."
Abstract
 Add to MetaCart
In any learnability setting, hypotheses are conjectured from some hypothesis space. Studied herein are the influence on learnability of the presence or absence of certain control structures in the hypothesis space. First presented are control structure characterizations of some rather specific
Statistical Analysis of Cointegrated Vectors
 Journal of Economic Dynamics and Control
, 1988
"... We consider a nonstationary vector autoregressive process which is integrated of order 1, and generated by i.i.d. Gaussian errors. We then derive the maximum likelihood estimator of the space of cointegration vectors and the likelihood ratio test of the hypothesis that it has a given number of dimen ..."
Abstract

Cited by 2749 (12 self)
 Add to MetaCart
We consider a nonstationary vector autoregressive process which is integrated of order 1, and generated by i.i.d. Gaussian errors. We then derive the maximum likelihood estimator of the space of cointegration vectors and the likelihood ratio test of the hypothesis that it has a given number
Learning quickly when irrelevant attributes abound: A new linearthreshold algorithm
 Machine Learning
, 1988
"... learning Boolean functions, linearthreshold algorithms Abstract. Valiant (1984) and others have studied the problem of learning various classes of Boolean functions from examples. Here we discuss incremental learning of these functions. We consider a setting in which the learner responds to each ex ..."
Abstract

Cited by 773 (5 self)
 Add to MetaCart
example according to a current hypothesis. Then the learner updates the hypothesis, if necessary, based on the correct classification of the example. One natural measure of the quality of learning in this setting is the number of mistakes the learner makes. For suitable classes of functions, learning
Results 1  10
of
4,539