Changes in synapse weights due to circuit drifts suppressed. Proposed fully parallel analog version of electronic neural-network processor based on delta-back-propagation algorithm. Processor able to "learn" when provided with suitable combinations of inputs and enforced outputs. Includes programmable resistive memory elements (corresponding to synapses), conductances (synapse weights) adjusted during learning. Buffer amplifiers, summing circuits, and sample-and-hold circuits arranged in layers of electronic neurons in accordance with delta-back-propagation algorithm.
Analog Delta-Back-Propagation Neural-Network Circuitry
NASA Tech Briefs ; 14 , 6
1990-06-01
Miscellaneous
No indication
English
Neural Network Back-Propagation Algorithm for Sensing Hypergols
Online Contents | 2013
Built-In Hardware for Analog Circuitry Testing
IEEE | 2008
|Fault Diagnosis of Rotating Machinery Using Back Propagation Neural Network
British Library Online Contents | 1997
|Predicting Ejection Velocity of Ejection Seat via Back Propagation Neural Network
Online Contents | 2011
|Simulation of Driver Behavior with Agent-Based Back-Propagation Neural Network
Online Contents | 2011
|