Title :
Real time output derivatives for on chip learning using digital stochastic bit stream neurons
Author :
Zhao, Junhua ; Shawe-Taylor, John
fDate :
10/13/1994 12:00:00 AM
Abstract :
The authors present the hardware design of an extremely compact and novel digital stochastic neuron, that has the ability to generate the derivative of its output with respect to an arbitrary input. These derivatives may be used to form the basis of an on chip gradient descent learning algorithm
Keywords :
learning (artificial intelligence); neural chips; real-time systems; stochastic automata; digital stochastic bit stream neurons; gradient descent learning algorithm; hardware design; onchip learning; real time output derivatives;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19941233