Application of Exponential Hetero-Associative Memory on Frequency Classifier

Abstract We present the auto- and hetero-associative memories incorporating the exponential encoding scheme in this paper. The condition that the evolution of the system energy can reach the global minimum state is presented. The improvement of the memory storage capacities of the exponential associative memories is discussed. The application of a frequency classifier is presented and the performance of associative memories with and without the exponential correlation function are compared. The exponential associative memory is superior in classifying the cluttered signals to the linear associative memory.

[1]  Heng-Ming Tai,et al.  Neural networks with higher-order nonlinearity , 1988 .

[2]  B Kosko,et al.  Adaptive bidirectional associative memories. , 1987, Applied optics.

[4]  C. L. Giles,et al.  High order correlation model for associative memory , 1987 .

[5]  B. Kosko,et al.  Feedback stability and unsupervised learning , 1988, IEEE 1988 International Conference on Neural Networks.

[6]  Baldi,et al.  Number of stable points for spin-glasses and neural networks of higher orders. , 1987, Physical review letters.

[7]  Demetri Psaltis,et al.  Higher order associative memories and their optical implementations , 1988, Neural Networks.

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

[9]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[10]  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.

[11]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[12]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.