Patent
1996-07-19
1997-12-23
Hafiz, Tariq R.
395 24, 395 21, G06F 1518
Patent
active
057013985
ABSTRACT:
A neural network including a plurality of sub-nets stored in a memory array and a method of operation. Each of the sub-nets includes a corresponding plurality of weights and is individually operable to classify an input vector. A computation unit, including a distance calculation unit and a math unit, is responsive to an input vector comprising input training features for determining a distance between the weights of each sub-net to each of the input features of the input vector and for determining whether the distance is within a particular region of influence. Also described is a parallel process for training the sub-nets.
REFERENCES:
patent: 5276771 (1994-01-01), Manukian et al.
IBM Microelectronics, ZISC.RTM., Zero Instruction Set Computer, Preliminary Information , Apr. 1994, pp. 31-39 .
Cole John
Glier Michael T.
Laird Mark
Hafiz Tariq R.
Nestor, Inc.
LandOfFree
Adaptive classifier having multiple subnetworks does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Adaptive classifier having multiple subnetworks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive classifier having multiple subnetworks will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1807019