论文信息 - An impulse realization of short-term-memory dynamics

An impulse realization of short-term-memory dynamics

Impulse neural networks use pulse sequences to communicate instantaneous neuron activation levels. CMOS electronic circuits which emulate chemical and voltage-gated membrane channels and communicate in a fashion similar to that of natural neurons are described. These circuits require less area and dissipate less power than the operational amplifier realizations previously used for continuous-time neural network implementation. An impulse network which realizes general short-term memory dynamics is discussed.<<ETX>>

[1] B. V. K. Vijaya Kumar,et al. Emulating the dynamics for a class of laterally inhibited neural networks , 1989, Neural Networks.

[2] Bahram Nabet,et al. Analog Implementation of Shunting Neural Networks , 1988, NIPS.

[3] Jack L. Meador,et al. A Low-Power CMOS Circuit Which Emulates Temporal Electrical Properties of Neurons , 1988, NIPS.

[4] Stephen Grossberg,et al. A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[5] 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.