System and method for designing fixed weight analog neural netwo

Boots – shoes – and leggings

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

364488, G06F 1518

Patent

active

057178330

ABSTRACT:
A system and method for designing a fixed weight analog neural network to perform analog signal processing allows the neural network to be designed with off-line training and implemented with low precision components. A global system error is iteratively computed in accordance with initialized neural functions and weights corresponding to a desired analog neural network configuration for analog signal processing. The neural weights are selectively modified during training and then expected values of weight implementation errors are added thereto. The error adjusted neural weights are used to recompute the global system error and the result thereof is compared to a desired global system error. These steps are repeated as long as the recomputed global system error is greater than the desired global system error. Following that, MOSFET parameters representing MOSFET channel widths and lengths are computed which correspond to the neural functions and weights. Such MOSFET device parameters are then used to implement the desired analog neural network configuration.

REFERENCES:
patent: 5222193 (1993-06-01), Brooks
patent: 5293458 (1994-03-01), Chung
patent: 5347613 (1994-09-01), Chung
patent: 5519811 (1996-05-01), Yoneda
Eberhardt, "Design of hardware neural network systems from custom analog vlsi builing block chips," IJCNN; Jun. 18-22, 1989, vol. 2.
Mead, "Analog vlsi implementation of neural systems," Chapter 9, Kluwer academic publishers, Boston, Dec. 1989.
Rossetto, "Analog vlsi synaptic matrices as building blocks for neural networks," IEEE micro, Dec. 1989.
Faggin, "VLSI implementation of neural networks," An introduction to neural and electronic networks, Academic Press, Inc., Dec. 1990.
Hiroshi Ishii, Tadashi Shibata, Hideo Kosaka and Tadahiro Ohmi, "Hardware-Backpropagation Learning of Neuron MOS Neural Networks", 1992 IEEE, pp. 16.4.1-16.4.4.
W. Shields Neely and Chwan-Hwa John Wu, "A New Training Method for Precision-Limited Analog Neural Networks", 1994 IEEE, pp. 2022-2027.
Koji Kotani, Tadashi Shibata and Tadahiro Ohmi, "Neuron-MOS Binary-Logic Circuits Featuring Dramatic Reduction in Transistor Count and Interconnections", 1992 IEEE, pp. 16.3.1-16.3.4.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

System and method for designing fixed weight analog neural netwo does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System and method for designing fixed weight analog neural netwo, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for designing fixed weight analog neural netwo will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2085082

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.