Results 1  10
of
2,212
The Nature of Statistical Learning Theory
, 1995
"... Abstract—Statistical learning theory was introduced in the late 1960’s. Until the 1990’s it was a purely theoretical analysis of the problem of function estimation from a given collection of data. In the middle of the 1990’s new types of learning algorithms (called support vector machines) based on ..."
Abstract

Cited by 8980 (27 self)
 Add to MetaCart
Abstract—Statistical learning theory was introduced in the late 1960’s. Until the 1990’s it was a purely theoretical analysis of the problem of function estimation from a given collection of data. In the middle of the 1990’s new types of learning algorithms (called support vector machines) based on the developed theory were proposed. This made statistical learning theory not only a tool for the theoretical analysis but also a tool for creating practical algorithms for estimating multidimensional functions. This article presents a very general overview of statistical learning theory including both theoretical and algorithmic aspects of the theory. The goal of this overview is to demonstrate how the abstract learning theory established conditions for generalization which are more general than those discussed in classical statistical paradigms and how the understanding of these conditions inspired new algorithmic approaches to function estimation problems.
SupportVector Networks
 Machine Learning
, 1995
"... The supportvector network is a new learning machine for twogroup classification problems. The machine conceptually implements the following idea: input vectors are nonlinearly mapped to a very highdimension feature space. In this feature space a linear decision surface is constructed. Special pr ..."
Abstract

Cited by 2171 (31 self)
 Add to MetaCart
The supportvector network is a new learning machine for twogroup classification problems. The machine conceptually implements the following idea: input vectors are nonlinearly mapped to a very highdimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the supportvector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to nonseparable training data.
Finding structure in time
 COGNITIVE SCIENCE
, 1990
"... Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather than explicitly (as in a spatial representation). The current report develops a pro ..."
Abstract

Cited by 1542 (21 self)
 Add to MetaCart
Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather than explicitly (as in a spatial representation). The current report develops a proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory. In this approach, hidden unit patterns are fed back to themselves; the internal representations which develop thus reflect task demands in the context of prior internal states. A set of simulations is reported which range from relatively simple problems (temporal version of XOR) to discovering syntactic/semantic features for words. The networks are able to learn interesting internal representations which incorporate task demands with memory demands; indeed, in this approach the notion of memory is inextricably bound up with task processing. These representations reveal a rich structure, which allows them to be highly contextdependent while also expressing generalizations across classes of items. These representations suggest a method for representing lexical categories and the type/token distinction.
Learning to predict by the methods of temporal differences
 MACHINE LEARNING
, 1988
"... This article introduces a class of incremental learning procedures specialized for prediction – that is, for using past experience with an incompletely known system to predict its future behavior. Whereas conventional predictionlearning methods assign credit by means of the difference between predi ..."
Abstract

Cited by 1227 (45 self)
 Add to MetaCart
This article introduces a class of incremental learning procedures specialized for prediction – that is, for using past experience with an incompletely known system to predict its future behavior. Whereas conventional predictionlearning methods assign credit by means of the difference between predicted and actual outcomes, the new methods assign credit by means of the difference between temporally successive predictions. Although such temporaldifference methods have been used in Samuel's checker player, Holland's bucket brigade, and the author's Adaptive Heuristic Critic, they have remained poorly understood. Here we prove their convergence and optimality for special cases and relate them to supervisedlearning methods. For most realworld prediction problems, temporaldifference methods require less memory and less peak computation than conventional methods and they produce more accurate predictions. We argue that most problems to which supervised learning is currently applied are really prediction problems of the sort to which temporaldifference methods can be applied to advantage.
Intelligence without reason
 COMPUTERS AND THOUGHT, IJCAI91
, 1991
"... Computers and Thought are the two categories that together define Artificial Intelligence as a discipline. It is generally accepted that work in Artificial Intelligence over the last thirty years has had a strong influence on aspects of computer architectures. In this paper we also make the conver ..."
Abstract

Cited by 757 (9 self)
 Add to MetaCart
Computers and Thought are the two categories that together define Artificial Intelligence as a discipline. It is generally accepted that work in Artificial Intelligence over the last thirty years has had a strong influence on aspects of computer architectures. In this paper we also make the converse claim; that the state of computer architecture has been a strong influence on our models of thought. The Von Neumann model of computation has lead Artificial Intelligence in particular directions. Intelligence in biological systems is completely different. Recent work in behaviorbased Artificial Intelligence has produced new models of intelligence that are much closer in spirit to biological systems. The nonVon Neumann computational models they use share many characteristics with biological computation.
Gradientbased learning applied to document recognition
 Proceedings of the IEEE
, 1998
"... Multilayer neural networks trained with the backpropagation algorithm constitute the best example of a successful gradientbased learning technique. Given an appropriate network architecture, gradientbased learning algorithms can be used to synthesize a complex decision surface that can classify hi ..."
Abstract

Cited by 732 (58 self)
 Add to MetaCart
Multilayer neural networks trained with the backpropagation algorithm constitute the best example of a successful gradientbased learning technique. Given an appropriate network architecture, gradientbased learning algorithms can be used to synthesize a complex decision surface that can classify highdimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of two dimensional (2D) shapes, are shown to outperform all other techniques. Reallife document recognition systems are composed of multiple modules including field extraction, segmentation, recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN’s), allows such multimodule systems to be trained globally using gradientbased methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank check is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal checks. It is deployed commercially and reads several million checks per day.
Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods
 ADVANCES IN LARGE MARGIN CLASSIFIERS
, 1999
"... The output of a classifier should be a calibrated posterior probability to enable postprocessing. Standard SVMs do not provide such probabilities. One method to create probabilities is to directly train a kernel classifier with a logit link function and a regularized maximum likelihood score. Howev ..."
Abstract

Cited by 701 (0 self)
 Add to MetaCart
The output of a classifier should be a calibrated posterior probability to enable postprocessing. Standard SVMs do not provide such probabilities. One method to create probabilities is to directly train a kernel classifier with a logit link function and a regularized maximum likelihood score. However, training with a maximum likelihood score will produce nonsparse kernel machines. Instead, we train an SVM, then train the parameters of an additional sigmoid function to map the SVM outputs into probabilities. This chapter compares classification error rate and likelihood scores for an SVM plus sigmoid versus a kernel method trained with a regularized likelihood error function. These methods are tested on three dataminingstyle data sets. The SVM+sigmoid yields probabilities of comparable quality to the regularized maximum likelihood kernel method, while still retaining the sparseness of the SVM.
Solving multiclass learning problems via errorcorrecting output codes
 Journal of Artificial Intelligence Research
, 1995
"... Multiclass learning problems involve nding a de nition for an unknown function f(x) whose range is a discrete set containing k>2values (i.e., k \classes"). The de nition is acquired by studying collections of training examples of the form hx i;f(x i)i. Existing approaches to multiclass learning ..."
Abstract

Cited by 569 (9 self)
 Add to MetaCart
Multiclass learning problems involve nding a de nition for an unknown function f(x) whose range is a discrete set containing k>2values (i.e., k \classes"). The de nition is acquired by studying collections of training examples of the form hx i;f(x i)i. Existing approaches to multiclass learning problems include direct application of multiclass algorithms such as the decisiontree algorithms C4.5 and CART, application of binary concept learning algorithms to learn individual binary functions for each of the k classes, and application of binary concept learning algorithms with distributed output representations. This paper compares these three approaches to a new technique in which errorcorrecting codes are employed as a distributed output representation. We show that these output representations improve the generalization performance of both C4.5 and backpropagation on a wide range of multiclass learning tasks. We also demonstrate that this approach is robust with respect to changes in the size of the training sample, the assignment of distributed representations to particular classes, and the application of over tting avoidance techniques such as decisiontree pruning. Finally,we show thatlike the other methodsthe errorcorrecting code technique can provide reliable class probability estimates. Taken together, these results demonstrate that errorcorrecting output codes provide a generalpurpose method for improving the performance of inductive learning programs on multiclass problems. 1.
Parallel Networks that Learn to Pronounce English Text
 COMPLEX SYSTEMS
, 1987
"... This paper describes NETtalk, a class of massivelyparallel network systems that learn to convert English text to speech. The memory representations for pronunciations are learned by practice and are shared among many processing units. The performance of NETtalk has some similarities with observed h ..."
Abstract

Cited by 455 (5 self)
 Add to MetaCart
This paper describes NETtalk, a class of massivelyparallel network systems that learn to convert English text to speech. The memory representations for pronunciations are learned by practice and are shared among many processing units. The performance of NETtalk has some similarities with observed human performance. (i) The learning follows a power law. (;i) The more words the network learns, the better it is at generalizing and correctly pronouncing new words, (iii) The performance of the network degrades very slowly as connections in the network are damaged: no single link or processing unit is essential. (iv) Relearning after damage is much faster than learning during the original training. (v) Distributed or spaced practice is more effective for longterm retention than massed practice. Network models can be constructed that have the same performance and learning characteristics on a particular task, but differ completely at the levels of synaptic strengths and singleunit responses. However, hierarchical clustering techniques applied to NETtalk reveal that these different networks have similar internal representations of lettertosound correspondences within groups of processing units. This suggests that invariant internal representations may be found in assemblies of neurons intermediate in size between highly localized and completely distributed representations.
The use of the area under the ROC curve in the evaluation of machine learning algorithms
 Pattern Recognition
, 1997
"... AbstractIn this paper we investigate the use of the area under the receiver operating characteristic (ROC) curve (AUC) as a performance measure for machine learning algorithms. As a case study we evaluate six machine learning algorithms (C4.5, Multiscale Classifier, Perceptron, Multilayer Percept ..."
Abstract

Cited by 435 (0 self)
 Add to MetaCart
AbstractIn this paper we investigate the use of the area under the receiver operating characteristic (ROC) curve (AUC) as a performance measure for machine learning algorithms. As a case study we evaluate six machine learning algorithms (C4.5, Multiscale Classifier, Perceptron, Multilayer Perceptron, kNearest Neighbours, and a Quadratic Discriminant Function) on six "real world " medical diagnostics data sets. We compare and discuss the use of AUC to the more conventional overall accuracy and find that AUC exhibits a number of desirable properties when compared to overall accuracy: increased sensitivity in Analysis of Variance (ANOVA) tests; a standard error that decreased as both AUC and the number of test samples increased; decision threshold independent; and it is invariant to a priori class probabilities. The paper concludes with the recommendation that AUC be used in preference to overall accuracy for "single number " evaluation of machine