A programmable analog neural network processor

An analog neural network breadboard consisting of 256 neurons and 2048 programmable synaptic weights of 5 bits each is constructed and tested. The heart of the processor is an array of custom-programmable synapse (resistor) chips on a reconfigurable neuron board. The analog bandwidth of the system is 90 kHz. The breadboard is used to demonstrate the application of neural network learning to the problem of real-time adaptive mirror control. The processor control is 21 actuators of an adaptive mirror with a step-response setting time of 5 ms. The demonstration verified that it is possible to modify the control law of the high-speed analog loop using neural network training without stopping the control loop.

[1]  A. Masaki,et al.  Neural networks in CMOS: a case study , 1990, IEEE Circuits and Devices Magazine.

[2]  R. C. Smithson,et al.  Implementation of the Hopfield decomposition and DFT into analog hardware , 1989, International 1989 Joint Conference on Neural Networks.

[3]  Paul Ehrensberger,et al.  High Speed, Large Format Wavefront Sensor Employing Hexflash Phase Analysis , 1989, Optics & Photonics.

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

[5]  D. S. Acton.  Results from the Lockheed solar adaptive optics system , 1989 .

[6]  J. I. Raffel,et al.  A generic architecture for wafer-scale neuromorphic systems , 1990 .

[7]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[8]  R. Hudgin.  Wave-front reconstruction for compensated imaging , 1977 .

[9]  Robert C. Smithson.  A Segmented Active Mirror For Solar Observations , 1987, Other Conferences.

[10]  L.D. Jackel,et al.  Analog electronic neural network circuits , 1989, IEEE Circuits and Devices Magazine.

[11]  J. Hardy,et al.  Real-time atmospheric compensation , 1977 .

[12]  Robert Carroll Smithson,et al.  Application of the Lockheed programmable analog neural network breadboard to the real-time adaptive mirror control problem , 1990, Defense, Security, and Sensing.

[13]  Richard H. Hudgin,et al.  Optimal wave-front estimation , 1977 .