Results 1  10
of
43
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 2155 (32 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.
Simple statistical gradientfollowing algorithms for connectionist reinforcement learning
 Machine Learning
, 1992
"... Abstract. This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units. These algorithms, called REINFORCE algorithms, are shown to make weight adjustments in a direction that lies along the gradient of expected reinfor ..."
Abstract

Cited by 321 (0 self)
 Add to MetaCart
Abstract. This article presents a general class of associative reinforcement learning algorithms for connectionist networks containing stochastic units. These algorithms, called REINFORCE algorithms, are shown to make weight adjustments in a direction that lies along the gradient of expected reinforcement in both immediatereinforcement tasks and certain limited forms of delayedreinforcement tasks, and they do this without explicitly computing gradient estimates or even storing information from which such estimates could be computed. Specific examples of such algorithms are presented, some of which bear a close relationship to certain existing algorithms while others are novel but potentially interesting in their own right. Also given are results that show how such algorithms can be naturally integrated with backpropagation. We close with a brief discussion of a number of additional issues surrounding the use of such algorithms, including what is known about their limiting behaviors as well as further considerations that might be used to help develop similar but potentially more powerful reinforcement learning algorithms.
An empirical study of learning speed in backpropagation networks
, 1988
"... Most connectionist or "neural network" learning systems use some form of the backpropagation algorithm. However, backpropagation learning is too slow for many applications, and it scales up poorly as tasks become larger and more complex. The factors governing learning speed are poorly understood. ..."
Abstract

Cited by 224 (0 self)
 Add to MetaCart
Most connectionist or "neural network" learning systems use some form of the backpropagation algorithm. However, backpropagation learning is too slow for many applications, and it scales up poorly as tasks become larger and more complex. The factors governing learning speed are poorly understood. I have begun a systematic, empirical study of learning speed in backproplike algorithms, measured against a variety of benchmark problems. The goal is twofold: to develop faster learning algorithms and to contribute to the development of a methodology that will be of value in future studies of this kind. This paper is a progress report describing the results obtained during the first six months of this study. To date I have looked only at a limited set of benchmark problems, but the results on these are encouraging: I have developed a new learning algorithm that is faster than standard backprop by an order of magnitude or more and that appears to scale up very well as the problem size increases.
Task Decomposition Through Competition in a Modular Connectionist Architecture
 COGNITIVE SCIENCE
, 1990
"... A novel modular connectionist architecture is presented in which the networks composing the architecture compete to learn the training patterns. As a result of the competition, different networks learn different training patterns and, thus, learn to compute different functions. The architecture pe ..."
Abstract

Cited by 181 (5 self)
 Add to MetaCart
A novel modular connectionist architecture is presented in which the networks composing the architecture compete to learn the training patterns. As a result of the competition, different networks learn different training patterns and, thus, learn to compute different functions. The architecture performs task decomposition in the sense that it learns to partition a task into two or more functionally independent vii tasks and allocates distinct networks to learn each task. In addition, the architecture tends to allocate to each task the network whose topology is most appropriate to that task, and tends to allocate the same network to similar tasks and distinct networks to dissimilar tasks. Furthermore, it can be easily modified so as to...
Gradient calculation for dynamic recurrent neural networks: a survey
 IEEE Transactions on Neural Networks
, 1995
"... Abstract  We survey learning algorithms for recurrent neural networks with hidden units, and put the various techniques into a common framework. We discuss xedpoint learning algorithms, namely recurrent backpropagation and deterministic Boltzmann Machines, and non xedpoint algorithms, namely backp ..."
Abstract

Cited by 135 (3 self)
 Add to MetaCart
Abstract  We survey learning algorithms for recurrent neural networks with hidden units, and put the various techniques into a common framework. We discuss xedpoint learning algorithms, namely recurrent backpropagation and deterministic Boltzmann Machines, and non xedpoint algorithms, namely backpropagation through time, Elman's history cuto, and Jordan's output feedback architecture. Forward propagation, an online technique that uses adjoint equations, and variations thereof, are also discussed. In many cases, the uni ed presentation leads to generalizations of various sorts. We discuss advantages and disadvantages of temporally continuous neural networks in contrast to clocked ones, continue with some \tricks of the trade" for training, using, and simulating continuous time and recurrent neural networks. We present somesimulations, and at the end, address issues of computational complexity and learning speed.
Reinforcement Learning And Its Application To Control
, 1992
"... Learning control involves modifying a controller's behavior to improve its performance as measured by some predefined index of performance (IP). If control actions that improve performance as measured by the IP are known, supervised learning methods, or methods for learning from examples, can be us ..."
Abstract

Cited by 51 (2 self)
 Add to MetaCart
Learning control involves modifying a controller's behavior to improve its performance as measured by some predefined index of performance (IP). If control actions that improve performance as measured by the IP are known, supervised learning methods, or methods for learning from examples, can be used to train the controller. But when such control actions are not known a priori, appropriate control behavior has to be inferred from observations of the IP. One can distinguish between two classes of methods for training controllers under such circumstances. Indirect methods involve constructing a model of the problem's IP and using the model to obtain training information for the controller. On the other hand, direct, or modelfree,...
Discovering Neural Nets With Low Kolmogorov Complexity And High Generalization Capability
 Neural Networks
, 1997
"... Many neural net learning algorithms aim at finding "simple" nets to explain training data. The expectation is: the "simpler" the networks, the better the generalization on test data (! Occam's razor). Previous implementations, however, use measures for "simplicity" that lack the power, universali ..."
Abstract

Cited by 50 (31 self)
 Add to MetaCart
Many neural net learning algorithms aim at finding "simple" nets to explain training data. The expectation is: the "simpler" the networks, the better the generalization on test data (! Occam's razor). Previous implementations, however, use measures for "simplicity" that lack the power, universality and elegance of those based on Kolmogorov complexity and Solomonoff's algorithmic probability. Likewise, most previous approaches (especially those of the "Bayesian" kind) suffer from the problem of choosing appropriate priors. This paper addresses both issues. It first reviews some basic concepts of algorithmic complexity theory relevant to machine learning, and how the SolomonoffLevin distribution (or universal prior) deals with the prior problem. The universal prior leads to a probabilistic method for finding "algorithmically simple" problem solutions with high generalization capability. The method is based on Levin complexity (a timebounded generalization of Kolmogorov comple...
Connectionism and the study of change
 Brain Development and Cognition: A Reader
, 1993
"... Developmental psychology and developmental neuropsychology have traditionally focused on the study of children. But these two fields are also supposed to be about the study of change, i.e. changes in behavior, changes in the neural structures that underlie behavior, and changes in the relationship b ..."
Abstract

Cited by 32 (0 self)
 Add to MetaCart
Developmental psychology and developmental neuropsychology have traditionally focused on the study of children. But these two fields are also supposed to be about the study of change, i.e. changes in behavior, changes in the neural structures that underlie behavior, and changes in the relationship between mind and brain across the course of development. Ironically, there has been relatively little interest in the mechanisms responsible for change in the last 15–20 years of developmental research. The reasons for this deemphasis on change have a great deal to do with a metaphor for mind and brain that has influenced most of experimental psychology, cognitive science and neuropsychology for the last few decades, i.e. the metaphor of the serial digital computer. We will refer to this particu
Measuring Invariances in Deep Networks
"... For many pattern recognition tasks, the ideal input feature would be invariant to multiple confounding properties (such as illumination and viewing angle, in computer vision applications). Recently, deep architectures trained in an unsupervised manner have been proposed as an automatic method for ex ..."
Abstract

Cited by 28 (7 self)
 Add to MetaCart
For many pattern recognition tasks, the ideal input feature would be invariant to multiple confounding properties (such as illumination and viewing angle, in computer vision applications). Recently, deep architectures trained in an unsupervised manner have been proposed as an automatic method for extracting useful features. However, it is difficult to evaluate the learned features by any means other than using them in a classifier. In this paper, we propose a number of empirical tests that directly measure the degree to which these learned features are invariant to different input transformations. We find that stacked autoencoders learn modestly increasingly invariant features with depth when trained on natural images. We find that convolutional deep belief networks learn substantially more invariant features in each layer. These results further justify the use of “deep ” vs. “shallower ” representations, but suggest that mechanisms beyond merely stacking one autoencoder on top of another may be important for achieving invariance. Our evaluation metrics can also be used to evaluate future work in deep learning, and thus help the development of future algorithms. 1
An Incremental Gradient(Projection) Method With Momentum Term And Adaptive Stepsize Rule
 SIAM J. on Optimization
, 1998
"... . We consider an incremental gradient method with momentum term for minimizing the sum of continuously di#erentiable functions. This method uses a new adaptive stepsize rule that decreases the stepsize whenever su#cient progress is not made. We show that if the gradients of the functions are bounded ..."
Abstract

Cited by 25 (1 self)
 Add to MetaCart
. We consider an incremental gradient method with momentum term for minimizing the sum of continuously di#erentiable functions. This method uses a new adaptive stepsize rule that decreases the stepsize whenever su#cient progress is not made. We show that if the gradients of the functions are bounded and Lipschitz continuous over a certain level set, then every cluster point of the iterates generated by the method is a stationary point. In addition, if the gradient of the functions have a certain growth property, then the method is either linearly convergent in some sense or the stepsizes are bounded away from zero. The new stepsize rule is much in the spirit of heuristic learning rules used in practice for training neural networks via backpropagation. As such, the new stepsize rule may suggest improvements on existing learning rules. Finally, extension of the method and the convergence results to constrained minimization is discussed, as are some implementation issues and numerical exp...