Neural network architecture based on summation of phase-coherent

Details Neural network architecture based on summation of phase-coherent Neural network architecture based on summation of phase-coherent

1991-05-31

1993-11-09

MacDonald, Allen R.

Boots, shoes, and leggings

395 2, 364807, G06F 1518, G06G 700

Patent

active

052610357

ABSTRACT:
A neural network architecture has phase-coherent alternating current neural input signals. Each input v.sub.k.sup.in is a two-phase pair of signals 180 degrees out of phase. Capacitive coupling of both signals of n input pairs to a summation line gives a non-dissipative realization of the weighted sum ##EQU1## with general real neural weights w.sub.ik. An alternating current offset signal proportional to u.sub.i is also capacitively coupled to the summation line. The signal on the summation line is passed through a low input capacitance follower/amplifier, a rectifier and a filter, producing a direct current signal proportional to the magnitude ##EQU2## This signal is compared with a direct current threshold proportional to t.sub.i, and the resultant is used to gate a two-phase alternating current output signal. The output is therefore functionally related to the inputs by ##EQU3## with .theta. the Heaviside step function. This generalized neuron can directly compute the "Exclusive Or" (XOR) logical operation. Alternative forms of the alternating current neuron using phase-shifters permit complex number inputs, outputs and neural weightings.

REFERENCES:
patent: 3287649 (1966-11-01), Rosenblatt
patent: 4660166 (1987-04-01), Hopfield
patent: 4719591 (1988-01-01), Hopfield et al.
patent: 4731747 (1988-03-01), Denker
patent: 4782460 (1988-11-01), Spencer
patent: 4839700 (1989-06-01), Ramesham et al.
patent: 4942367 (1990-07-01), Milkovic
patent: 4959532 (1990-09-01), Owechko
patent: 5063417 (1991-11-01), Hopfield
patent: 5063601 (1991-11-01), Hayduic
patent: 5107442 (1992-04-01), Weideman
patent: 5115492 (1992-05-01), Engeler
patent: 5124918 (1992-06-01), Beer et al.
"Simple `Neural` Optimration Network" Tauic et al., Trans. on Cir. and systems, IEEE 1986.
"Neural computing" Wasserman et al., Apr. 1989.
A Purely Capacitive Synaptic Matrix for Fixed-Weight Neural Networks by Ugur Cilingiroglu, IEEE Transactions on Circuits and Systems, vol. 38, No. 2, Feb. 1991.
Speech Recognition Network with SC Neuron-Like Components by Horio, et al., Dept. of Electronic Eng., Tokyo Denki Univ., 1988 IEEE.
Discrete-State Phasor Neural Networks by Andre J. Noest, Physical Review A, vol. 38, No. 4, Aug. 15, 1988.
Adaptive Optical Networks Using Photorefractive Crystals by Psaltis, et al., Applied Optics, vol. 27, Aug. 15, 1988.
Adaptive Optical Networks Using Photorefractive Crystals by Psaltis, et al., Applied Optics, vol. 27, No. 9, May 1, 1988.
Neural Computing, Theory and Practice by Philip D. Wasserman, Anza Research, Inc., May 1, 1990.
Introduction to the Theory of Neural Computation by Hertz, et al., Santa Fe Institute.
Switched-Capacitor Neural Networks by Tsividis, et al., Jul. 8, 1987 Electronics Letters Aug. 27, 1987, vol. 23, No. 18.

Affiliated with

Also associated with

Rating

Neural network architecture based on summation of phase-coherent does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural network architecture based on summation of phase-coherent, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network architecture based on summation of phase-coherent will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1149254