Recognition by constructive neural algorithms

The usability of the constructive neural algorithms as pattern classifiers is investigated. It is pointed out that the unboundedness of the decision regions formed by most neural recognizers leads to substantial limitations of the generalization capabilities of these nets. We specify a constructive neural recognizer that forms bounded decision regions, and report the results of this algorithm on a series of benchmark problems that resemble the usual pattern recognition problems.

[1]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[2]  Jean-Pierre Nadal,et al.  Study of a Growth Algorithm for a Feedforward Network , 1989, Int. J. Neural Syst..

[3]  Y. Lee.  Handwritten digit recognition using k nearest neighbour radial-basis function, and backpropagation , 1991 .

[4]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

[5]  J. Schmee.  An Introduction to Multivariate Statistical Analysis , 1986 .

[6]  E. Oja.  Simplified neuron model as a principal component analyzer , 1982, Journal of mathematical biology.

[7]  Marcus Frean,et al.  The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks , 1990, Neural Computation.

[8]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[9]  Stephen I. Gallant,et al.  Perceptron-based learning algorithms , 1990, IEEE Trans. Neural Networks.

[10]  Larry D. Hostetler,et al.  Optimization of k nearest neighbor density estimates , 1973, IEEE Trans. Inf. Theory.

[11]  James A. Pittman,et al.  Recognizing Hand-Printed Letters and Digits Using Backpropagation Learning , 1991, Neural Computation.

[12]  Marcus R. Frean,et al.  A "Thermal" Perceptron Learning Rule , 1992, Neural Computation.

[13]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[14]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[15]  Silvano Di Zenzo,et al.  Optical recognition of hand-printed characters of any size, position, and orientation , 1992, IBM J. Res. Dev..

[16]  Stephen I. Gallant.  A Practical Approach for Representing Context and for Performing Word Sense Disambiguation Using Neural Networks , 1991, Neural Computation.

[17]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[18]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[19]  Yuchun Lee,et al.  Handwritten Digit Recognition Using K Nearest-Neighbor, Radial-Basis Function, and Backpropagation Neural Networks , 1991, Neural Computation.

[20]  Stephen I. Gallant,et al.  A Practical Approach for Representing Context and for Performing Word Sense Disambiguation Using Neural Networks , 1991, Neural Computation.

[21]  Jirí Benes,et al.  On neural networks , 1990, Kybernetika.

[22]  Ralph Bernstein,et al.  Gaussian Maximum Likelihood and Contextual Classification Algorithms for Multicrop Classification , 1987, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[24]  Neil Burgess,et al.  3-D Object Classification: Application of a Constructive Algorithm , 1991, Int. J. Neural Syst..

[25]  Jean-Pierre Nadal,et al.  Neural trees: a new tool for classification , 1990 .

[26]  Terence D. Sanger,et al.  Optimal unsupervised learning in a single-layer linear feedforward neural network , 1989, Neural Networks.

[27]  J. Ariel Sirat,et al.  A Fast Neural Algorithm for Principal Component Analysis and Singular Value Decomposition , 1991, Int. J. Neural Syst..