Design and VLSI implementation of a unified synapse-neuron architecture

We describe the design and VLSI implementation of a unified synapse-neuron architecture for multi-layer neural networks. A new hybrid building block proposed for this purpose is formed by integrating a partial S-shape neural nonlinearity within a Multiplying DAC synapse. MDAC synapse contains modifications to simplify sign-bit circuit. Small analog circuits generate a distributed S-shape neural function by combining quadratic characteristics of four MOS transistors. The proposed modular neural network architecture features design simplicity and scalability, area efficiency, reduced interconnection problem, improved robustness and digital programmability. Based on the proposed scheme, we have considerably increased the synaptic density in the improved version of a programmable optically-coupled neural network.

[1]  Guangxia Liang,et al.  A novel photo BJT array for intelligent imaging , 1993, Proceedings of 36th Midwest Symposium on Circuits and Systems.

[2]  Yannis Tsividis,et al.  A reconfigurable VLSI neural network , 1992 .

[3]  Majid Ahmadi,et al.  A Large-swing High-Drive CMOS Buffer amplifier for a Wide Load Range , 1992, J. Circuits Syst. Comput..

[4]  W. C. Miller,et al.  An Intelligent Optical Sensor , 1995 .

[5]  Graham A. Jullien,et al.  A programmable intelligent optical sensor realization , 1994, Proceedings of 1994 37th Midwest Symposium on Circuits and Systems.

[6]  H. Withagen,et al.  Reducing the effect of quantization by weight scaling , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[7]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[8]  Alexander Moopenn,et al.  Digital-Analog Hybrid Synapse Chips for Electronic Neural Networks , 1989, NIPS.