22 March 1996 Noise and randomlike behavior in perceptrons: theory and application to protein structure prediction
Author Affiliations +
Abstract
In this paper we study the effective behavior of a single-layer perceptron that is forced to learn a noisy mapping (e.g. associations of patterns with classes). The effect of different kinds of noise on the output of the network is discussed as a function of the noise intensity. It is argued that noise induces a random-like component in the overall behavior of the perceptron which we describe in terms of independent biased random flights in the space of the weights. These random processes (one for each class) are ruled by probability distributions specified by the weights themselves. Our model is applied to the real world application of the prediction of protein secondary structures. Several observations made in this task domain are rationalized in terms of the present model that, among others, provides a link between the seeming existence of an upper bound for the prediction efficiency and the amount of noise in the mapping.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mario Compiani, Mario Compiani, Piero Fariselli, Piero Fariselli, Rita Casadio, Rita Casadio, } "Noise and randomlike behavior in perceptrons: theory and application to protein structure prediction", Proc. SPIE 2760, Applications and Science of Artificial Neural Networks II, (22 March 1996); doi: 10.1117/12.235949; https://doi.org/10.1117/12.235949
PROCEEDINGS
11 PAGES


SHARE
Back to Top