Behaviour of feed-forward neural networks in invariant track finding

We performed several simulations with feed-forward neural networks using an idealized tracking apparatus with tracks invariant under translation and roto-translation transformations. Input information was provided to the networks without any processing. We implemented 2 and 3 layer architectures up...

Full description

Saved in:
Bibliographic Details
Published in:Computer physics communications 1994, Vol.79 (3), p.364-372
Main Authors: Lanza, A., Vitulo, P., Cattaneo, C., Caresana, M., Panetsos, F.
Format: Article
Language:English
Subjects:
Algorithms for functional approximation
Exact sciences and technology
Mathematical methods in physics
Numerical approximation and analysis
Numerical simulation, solution of equations
Physics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We performed several simulations with feed-forward neural networks using an idealized tracking apparatus with tracks invariant under translation and roto-translation transformations. Input information was provided to the networks without any processing. We implemented 2 and 3 layer architectures up to 50 000 connections, and we tested the influence of parameters such as learning rate, momentum, number of learning files and noise rejection on the classification efficiency. The generalization ability is not so good as expected, whereas the classification efficiency is larger than 90% for almost all the architectures, the influence of the above mentioned parameters being less than 10% overall except for the noise rejection for which it increases up to 20%.
ISSN:0010-4655
1879-2944
DOI:10.1016/0010-4655(94)90182-1