A hybrid architecture for feed-forward multi-layer neural networks

The building blocks of this architecture are mostly in analog CMOS to reduce the number of interconnecting wires. The memory, where the weights are stored, is implemented digitally to avoid the reliability and long-term preservation problems associated with the current analog storage schemes. The discrete nature of digital weights does not produce any problem in the application considered here, since the weights are pretrained. The number of connections to any layer is reduced to the same number as the neurons in the preceding layer without any loss in generality. The building blocks have been fabricated and tested. A proof-of-concept chip has also been designed in a double metal, single polysilicon, p-well CMOS process. With modest clocking speeds, the circuit will have latency times on the order of microseconds for practical problems.<<ETX>>

[1]  Fathi M. A. Salam,et al.  An all-MOS analog feedforward neural circuit with learning , 1990, IEEE International Symposium on Circuits and Systems.

[2]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

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

[4]  Michel Declercq,et al.  Implementation of a learning Kohonen neuron based on a new multilevel storage technique , 1991 .

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

[6]  Steven B. Bibyk,et al.  Programmable current-mode neural network for implementation in analogue MOS VLSI , 1990 .

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[8]  W. Hubbard,et al.  A programmable analog neural network chip , 1989 .

[9]  A. A. Abidi,et al.  An Analog CMOS Backward Error-propagation LSI , 1988, Twenty-Second Asilomar Conference on Signals, Systems and Computers.

[10]  D. Blackman,et al.  A general purpose analog neural computer , 1989, International 1989 Joint Conference on Neural Networks.

[11]  Eric A. Vittoz,et al.  Analog VLSI implementation of neural networks , 1990, IEEE International Symposium on Circuits and Systems.