Results 1  10
of
67,894
Submitted to Handbook of Brain Theory and Neural Networks, 2. Helmholtz Machines and WakeSleep Learning
"... Unsupervised learning is largely concerned with finding structure among sets of input patterns such as visual scenes. One important example of structure comes in cases that the input patterns are generated or caused in a systematic way, for instance when objects with different shapes, surface ..."
Abstract
 Add to MetaCart
Unsupervised learning is largely concerned with finding structure among sets of input patterns such as visual scenes. One important example of structure comes in cases that the input patterns are generated or caused in a systematic way, for instance when objects with different shapes, surface
In press: M. Arbib (Ed.), The Handbook of Brain Theory and Neural Networks. Cambridge, MA: MIT Press.
"... this article we discuss the problem of learning in modular and hierarchical systems. Modular and hierarchical systems allow complex learning problems to be solved by dividing the problem into a set of subproblems, each of which may be simpler to solve than the original problem. Within the context o ..."
Abstract
 Add to MetaCart
this article we discuss the problem of learning in modular and hierarchical systems. Modular and hierarchical systems allow complex learning problems to be solved by dividing the problem into a set of subproblems, each of which may be simpler to solve than the original problem. Within the context of supervised learningour focus in this articlemodular architectures arise when we assume that the data can be well described by a collection of functions, each of which is defined over a relatively local region of the input space. A modular architecture can model such data by allocating di#erent modules to di#erent regions of the space. Hierarchical architectures arise when we assume that the data are well described by a multiresolution modela model in which regions are divided recursively into subregions
Regularization Theory and Neural Networks Architectures
 Neural Computation
, 1995
"... We had previously shown that regularization principles lead to approximation schemes which are equivalent to networks with one layer of hidden units, called Regularization Networks. In particular, standard smoothness functionals lead to a subclass of regularization networks, the well known Radial Ba ..."
Abstract

Cited by 396 (33 self)
 Add to MetaCart
Basis Functions approximation schemes. This paper shows that regularization networks encompass a much broader range of approximation schemes, including many of the popular general additive models and some of the neural networks. In particular, we introduce new classes of smoothness functionals that lead
Complete discrete 2D Gabor transforms by neural networks for image analysis and compression
, 1988
"... AbstractA threelayered neural network is described for transforming twodimensional discrete signals into generalized nonorthogonal 2D “Gabor ” representations for image analysis, segmentation, and compression. These transforms are conjoint spatiahpectral representations [lo], [15], which provide ..."
Abstract

Cited by 475 (8 self)
 Add to MetaCart
AbstractA threelayered neural network is described for transforming twodimensional discrete signals into generalized nonorthogonal 2D “Gabor ” representations for image analysis, segmentation, and compression. These transforms are conjoint spatiahpectral representations [lo], [15], which
The Perceptron: A Probabilistic Model for Information Storage and Organization in The Brain
 Psychological Review
, 1958
"... If we are eventually to understand the capability of higher organisms for perceptual recognition, generalization, recall, and thinking, we must first have answers to three fundamental questions: 1. How is information about the physical world sensed, or detected, by the biological system? 2. In what ..."
Abstract

Cited by 1143 (0 self)
 Add to MetaCart
If we are eventually to understand the capability of higher organisms for perceptual recognition, generalization, recall, and thinking, we must first have answers to three fundamental questions: 1. How is information about the physical world sensed, or detected, by the biological system? 2. In what form is information stored, or remembered? 3. How does information contained in storage, or in memory, influence recognition and behavior? The first of these questions is in the
Results 1  10
of
67,894