Patent · US Expired

Method of increasing the accuracy of an analog neural network and the like

US5146602A · kind A · utility

44Cited by
5References
11Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 26, 1990
Grant dateSep 8, 1992
Priority date
Expiry dateDec 26, 2010

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG11C27/005
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for increasing the accuracy of an analog neural network which computers a sum-of-products between an input vector and a stored weight pattern is described. In one embodiment of the present invention, the method comprises initially training the network by programming the synapses with a certain weight pattern. The training may be carried out using any standard learning algorithm. Preferably, a back-propagation learning algorithm is employed. Next, network is baked at an elevated temperature to effectuate a change in the weight pattern previously programmed during initial training. This change results from a charge redistribution which occurs within each of the synapses of the network. After baking, the network is then retrained to compensate for the change resulting from the charge redistribution. The baking and retraining steps may be successively repeated to increase the accuracy of the neural network to any desired level.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.