Segmented neural network with daisy chain control

Details Segmented neural network with daisy chain control Segmented neural network with daisy chain control

1990-12-24

1993-05-25

MacDonald, Allen R.

G06F 1518

Patent

active

052147479

ABSTRACT:
The present invention is a direct digitally implemented network system in which neural nodes 24, 26 and 28 which output to the same destination node 22 in the network share the same channel 30. If a set of nodes does not output any data to any node to which a second set of nodes outputs data (the two sets of nodes to not overlap or intersect), the two sets of nodes are independent and do not share a channel and have separate channels 120 and 122. The network is configured as parallel operating non-intersecting segments or independent sets where each segment has a segment communication channel or bus 30. Each node in the independent set or segment is sequentially activated to produce an output by a daisy chain control signal. The outputs are thereby time division multiplexed over the channel 30 to the destination node 22. The nodes are implemented on integrated circuits 158 with multiple nodes per circuit. The outputs of the nodes on the circuits in a segment are connected to the segment channel. Each node includes a memory array 136 that stores the weights applied to each input via a multiplier 152. The multiplied inputs are accumulated and applied to a lookup table 132 that performs any threshold comparison operation. The output of the lookup table 134 is placed on a common bus serving as the channel for the independent set of nodes by a tristate driver 44 controlled by the daisy chain control signal.

REFERENCES:
patent: 4660166 (1987-04-01), Hopfield
patent: 4796199 (1989-01-01), Hammerstrom
patent: 4807168 (1989-02-01), Moopenn et al.
patent: 4809193 (1989-02-01), Jourjine
patent: 4918617 (1990-04-01), Hammerstrom
patent: 4974169 (1990-11-01), Engel
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5043913 (1991-08-01), Furutani
patent: 5060278 (1991-10-01), Fukumizu
patent: 5091864 (1992-02-01), Baji et al.
patent: 5142666 (1992-08-01), Yoshizawa et al.
Effects of Reinforcement on Knowledge Retrieval and Evaluation; S. Leven; IEEE Int. Conf. on Neural Networks; 1987; V. II; pp. 269-77.
Waveform Recognition Using Neural Networks; Palaz et al.; Geophysics: The Leading Edge of Exploration; Mar. 1990; pp. 28-31.
The VLSI Implementation of Stonn; Wike et al.; IJCNN 1990; vol. II; pp. 593-598.
VLSI Architectures for Neural Networks; Treleaven et al.; IEEE Micro; Dec. 1989; pp. 8-27.
A General Purpose Digital Architecture for Neural Network Simulations; Duranton et al.; First IEE Inter. Conf. on Artificial Neural Networks; 1989; pp. 62-66.
A Large Scale Neural Network "CombNET" and Its Application to Chinese Character Recognition; Iwata et al.; INNC; 1990; pp. 83-86.
Learning on VLSI: A General-Purpose Digital Neurochip; Duranton et al.; Philips Journal of Research; vol. 45, No. 1-17; 1990.
Design of Parallel Hardware Neural Network Systems from Custom Analog VLSI `Buildin Block` Chips; Eberhardt et al.; IJCNN; Jun. 1989; vol. 2; pp. 183-190.
A Study of Regular Architectures for Digital Implementation of Neural Networks; Suzuki et al.; IEEE Int. Symp. on Circuits and Systems; May 1989; pp. 82-85.
Masaki, IEEE Circuits and Devices Magazine, vol. 6, No. 4, Jul. 1990, New York, pp. 13-17.
J. J. Vidal, J. C. Pemberton and J. M. Goodwin, Implementing Neural Nets with Programmable Logic, pp. 539-545.
T. R. Martinez, Digital Neural Networks, pp. 681-684.
J. J. Vidal, Implementing Neural Nets with Programmable Logic, IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 36, No. 7, Jul. 1988, pp. 1180-1190.
L. A. Akers, M. R. Walker, D. K. Ferry, and R. O. Grondin, Limited Interconnectivity in Synthetic Neural Systems, pp. 407-417.
D. Hammerstrom, Solving Connectivity Problems in VLSI Neuron Nets, pp. 395-407.
J. I. Raffel, The Application of Wafer-Scale Technology to Neuromorphic Systems, pp. 202-222.
H. P. Graf, L. D. Jackel, and W. E. Hubbard, VLSI Implementation of a Neural Network Model, pp. 41-49.

Affiliated with

Also associated with

Rating

Segmented neural network with daisy chain control does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Segmented neural network with daisy chain control, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Segmented neural network with daisy chain control will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-904434