Hardware implementation of ART1 memories using a mixed analog/digital approach
暂无分享,去创建一个
This paper presents a VLSI circuit implementation for both the short-term memory (STM) and long-term memory (LTM) of the adaptive resonance theory neural network (ART1-NN). The circuit is implemented based on the transconductance-mode approach and mixed analog/digital components, in which analog circuits are used to fully incorporate the parallel mechanism of the neural network, whereas digital circuits provide a reduced circuit size as well as a more precise multiplication operation. A simple analog-to-digital (A/D) converter is also included to realize binary STM activities and characterize the quenching threshold. The PSpice simulation results of the implemented circuits are in good agreement with the exact solutions of the coupled nonlinear differential equations.<<ETX>>
[1] Stephen Grossberg,et al. Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.
[2] Stephen Grossberg,et al. A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..
[3] Carver Mead,et al. Analog VLSI and neural systems , 1989 .
[4] Edgar Sanchez-Sinencio,et al. A modular T-mode design approach for analog neural network hardware implementations , 1992 .