A hybrid cellular automaton/neural network classifier for multi-valued patterns and its VLSI implementation

Abstract A multi-valued pattern classifier with high discrimination sensitivity and its VLSI implementation proposal on a single chip are presented in this paper. The classification scheme is based on the combination of a reconfigurable Cellular Automaton and a Neural Network architecture. A 2-D Reconfigurable Hybrid Additive Cellular Automaton (RHACA) architecture amplifies the Hamming distance between patterns, whereas a neural network architecture, implemented in digital form, assigns vectors of weighing coefficients which take into account the relative significance of the sites on the 2-D lattice. The proposed classifier is able to operate successfully even for pattern classes of small difference, or for patterns that lie on the decision boundaries between classes. If the training and processing phases are not partitioned, the proposed classification scheme is able to operate in partially exposed environments. With the proper setting of admittance levels into the classes of multi-valued patterns involved, the proposed classifier can also operate on patterns with partly missing data. The proposed multi-valued pattern classifier can be realized on a single VLSI chip with dimensions 7.73 mm × 8.14 mm = 62.96 mm2 and the expected frequency of operation for the chip is 50 MHz.

[1]  B V Kumar,et al.  Evaluation of the use of the Hopfield neural network model as a nearest-neighbor algorithm. , 1986, Applied optics.

[2]  Fumitaka Kimura,et al.  Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  S. Wolfram.  Statistical mechanics of cellular automata , 1983 .

[4]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[5]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[6]  John K. Dixon,et al.  Pattern Recognition with Partly Missing Data , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  Howard C. Card,et al.  Group Properties of Cellular Automata and VLSI Applications , 1986, IEEE Transactions on Computers.

[8]  Ph. Tsalides.  Cellular automata-based built-in self-test structures for VLSI systems , 1990 .

[9]  Philippos Tsalides,et al.  Two-Dimensional Cellular Automata: Properties and Applications of a New VLSI Architecture , 1992, Comput. J..

[10]  Hon Keung Kwan.  One-layer feedforward neural network for fast maximum/minimum determination , 1992 .

[11]  R. Wong,et al.  Scene matching with invariant moments , 1978 .

[12]  Adonios Thanailakis,et al.  Design and VLSI implementation of mod-127 multiplier using cellular automaton-based data compression techniques , 1991 .

[13]  Andrew Luk,et al.  A Re-Examination of the Distance-Weighted k-Nearest Neighbor Classification Rule , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[14]  Howard C. Card,et al.  Cellular automata-based pseudorandom number generators for built-in self-test , 1989, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[15]  Panagiotis Tzionas,et al.  Cellular-automata-based learning network for pattern recognition , 1991, Other Conferences.

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

[17]  Stephen Thomas,et al.  ALL YOU NEED TO KNOW ABOUT... , 1996 .

[18]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[19]  A. Joussellin,et al.  A link between k-nearest neighbor rules and knowledge based systems by sequence analysis , 1987, Pattern Recognit. Lett..

[20]  S. Wolfram,et al.  Two-dimensional cellular automata , 1985 .

[21]  Julie Scoltock,et al.  A Survey of the Literature of Cluster Analysis , 1982, Comput. J..

[22]  Ivan Tomek,et al.  A Generalization of the k-NN Rule , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[23]  J. L. Hodges,et al.  Discriminatory Analysis - Nonparametric Discrimination: Small Sample Performance , 1952 .

[24]  J. L. Hodges,et al.  Discriminatory Analysis - Nonparametric Discrimination: Consistency Properties , 1989 .

[25]  Andrei Z. Broder,et al.  On the performance of edited nearest neighbor rules in high dimensions , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[26]  Panagiotis Tzionas,et al.  Design and VLSI implementation of a pattern classifier using pseudo 2D cellular automata , 1992 .

[27]  Kendall Preston,et al.  Modern Cellular Automata , 1984, Advanced Applications in Pattern Recognition.

[28]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[29]  Hugh B. Woodruff,et al.  An algorithm for a selective nearest neighbor decision rule (Corresp.) , 1975, IEEE Trans. Inf. Theory.