Analysis and synthesis of a class of discrete-time neural networks with multilevel threshold neurons

In contrast to the usual types of neural networks which utilize two states for each neuron, a class of synchronous discrete-time neural networks with multilevel threshold neurons is developed. A qualitative analysis and a synthesis procedure for the class of neural networks considered constitute the principal contributions of this paper. The applicability of the present class of neural networks is demonstrated by means of a gray level image processing example, where each neuron can assume one of sixteen values. When compared to the usual neural networks with two state neurons, networks which are endowed with multilevel neurons will, in general, for a given application, require fewer neurons and thus fewer interconnections. This is an important consideration in VLSI implementation.

[1]  Stephen Grossberg,et al.  Absolute stability of global pattern formation and parallel memory storage by competitive neural networks , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  A. Michel.  On the status of stability of interconnected systems , 1983 .

[3]  A. Michel,et al.  On stability preserving mappings , 1983 .

[4]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[5]  I. Guyon,et al.  Information storage and retrieval in spin-glass like neural networks , 1985 .

[6]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[7]  L. Personnaz,et al.  Collective computational properties of neural networks: New learning mechanisms. , 1986, Physical review. A, General physics.

[8]  Michael Fleisher.  The Hopfield Model with Multi-Level Neurons , 1987, NIPS.

[9]  Allon Guez,et al.  On the stability, storage capacity, and design of nonlinear continuous neural networks , 1988, IEEE Trans. Syst. Man Cybern..

[10]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[11]  Wolfgang Porod,et al.  Qualitative analysis and synthesis of a class of neural networks , 1988 .

[12]  R. Westervelt,et al.  Dynamics of iterated-map neural networks. , 1989, Physical review. A, General physics.

[13]  A. Michel,et al.  Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercube , 1989 .

[14]  D. Hansel,et al.  Information processing in three-state neural networks , 1989 .

[15]  J. Farrell,et al.  Qualitative analysis of neural networks , 1989 .

[16]  K. Sakurai,et al.  Organic Quantum Computing Systems For Electronic Brain , 1990, [1990] Proceedings of the Twelfth Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[17]  A.N. Michel,et al.  Associative memories via artificial neural networks , 1990, IEEE Control Systems Magazine.

[18]  Waugh,et al.  Associative memory in an analog iterated-map neural network. , 1990, Physical review. A, Atomic, molecular, and optical physics.

[19]  H. Rieger.  Properties of neural networks with multi-state neurons , 1990 .

[20]  B. Simic-Glavaski.  Molecular electronics and neural network functions , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[21]  Anthony N. Michel,et al.  Analysis and synthesis techniques for Hopfield type synchronous discrete time neural networks with application to associative memory , 1990 .

[22]  Clark Jeffries,et al.  Code recognition and set selection with neural networks , 1991, Mathematical modeling.