Title :
Compact building blocks for artificial neural networks
Author :
Meléndez-Rodríguez, M. ; Silva-Martínez, J.
Author_Institution :
Nat. Inst. of Astrophys. Opt. & Electron., Puebla, Mexico
fDate :
1/7/1999 12:00:00 AM
Abstract :
A four quadrant analogue multiplier, an activation function and a differentiator intended for the implementation of backpropagation algorithms are proposed. The priorities for the design are low-power, low-voltage, and minimum silicon area. Breadboard results, showing good agreement with the theoretical ones, are reported
Keywords :
analogue multipliers; backpropagation; differentiating circuits; low-power electronics; neural nets; activation function; analogue multiplier; artificial neural network; backpropagation algorithm; building block; differentiator; low-power low-voltage circuit; silicon area;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19990017