论文信息 - High-capacity exponential associative memories

High-capacity exponential associative memories

A generalized associative memory model with potentially high capacity is presented. A memory of this kind with M stored vectors of length N, can be implemented with M nonlinear neurons, N ordinary thresholding neurons, and 2MN binary synapses. It is shown that special cases of this model include the Hopfield and high-order correlation memories. A special case of the model, based on a neuron which can implement the subthreshold region, is presented. The authors analyze the capacity of this exponentially associative memory and show that it scales exponentially with N. In any practical realization, however, the dynamic range of the exponentiators is constrained. They show that the capacity for networks with fixed dynamic range exponential circuits is proportional to the dynamic range.<<ETX>>

Rodney M. Goodman | Tzi-Dar Chiueh

[1] B H Soffer,et al. Associative holographic memory with feedback using phase-conjugate mirrors. , 1986, Optics letters.

[2] Demetri Psaltis,et al. Nonlinear discriminant functions and associative memories , 1987 .

[3] Santosh S. Venkatesh,et al. The capacity of the Hopfield associative memory , 1987, IEEE Trans. Inf. Theory.

[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] Yuri Owechko. Holographic Associative Memories , 1990, Optics & Photonics.

[6] C. L. Giles,et al. Machine learning using higher order correlation networks , 1986 .

[7] Daniel W. Dobberpuhl,et al. The design and analysis of VLSI circuits , 1985 .

[8] Tzi-Dar Chiueh,et al. A Neural Network Classifier Based on Coding Theory , 1987, NIPS.

[9] 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.