Digital-Analog Hybrid Synapse Chips for Electronic Neural Networks

Cascadable, CMOS synapse chips containing a cross-bar array of 32×32 (1024) programmable synapses have been fabricated as "building blocks" for fully parallel implementation of neural networks. The synapses are based on a hybrid digital-analog design which utilizes on-Chip 7-bit data latches to store quantized weights and two-quadrant multiplying DAC's to compute weighted outputs. The synapses exhibit 6-bit resolution and excellent monotonicity and consistency in their transfer characteristics. A 64-neuron hardware incorporating four synapse chips has been fabricated to investigate the performance of feedback networks in optimization problem solving. In this study, a 7×7, one-to-one assignment net and the Hop field-Tank 8-city traveling salesman problem net have been implemented in the hardware. The network's ability to obtain optimum or near optimum solutions in real time has been demonstrated.

[1]  Taher Daud,et al.  Solid‐state thin‐film memistor for electronic neural networks , 1990 .

[2]  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.

[3]  A. Moopenn,et al.  Digital-Analog-Hybrid Neural Simulator: A Design-Aid For Custom-VLSI Neurochips , 1989, Photonics West - Lasers and Applications in Science and Engineering.

[4]  S K Khanna,et al.  Electronic hardware implementations of neural networks. , 1987, Applied optics.

[5]  S. Tam,et al.  An electrically trainable artificial neural network (ETANN) with 10240 'floating gate' synapses , 1990, International 1989 Joint Conference on Neural Networks.