A model of neural net activation dynamics with fixed random weights and a threshold on each site self-adjusting in function of the inner and unknown invariant of an input f(t) in noisy environments is proposed. This net is devoted to a real-time discrimination between different moving objects to furnish the net, by such preprocessing, with a coherent output for further processing. The main characteristic of the net is its ability to extract without a teacher an invariant of the input by a self-redefinition of the right covariance of the net dynamics forced by the outer input. An algebraic group formalization is proposed as well as a simulation application of the algorithm to the classical T-C in context discrimination problems
A non-linear neural net to extract symmetries from input f(t)
Morgavi G
1991
Abstract
A model of neural net activation dynamics with fixed random weights and a threshold on each site self-adjusting in function of the inner and unknown invariant of an input f(t) in noisy environments is proposed. This net is devoted to a real-time discrimination between different moving objects to furnish the net, by such preprocessing, with a coherent output for further processing. The main characteristic of the net is its ability to extract without a teacher an invariant of the input by a self-redefinition of the right covariance of the net dynamics forced by the outer input. An algebraic group formalization is proposed as well as a simulation application of the algorithm to the classical T-C in context discrimination problemsI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.