top
logo

Login Form



Visitors Counter

mod_vvisit_counterToday35
mod_vvisit_counterYesterday52
mod_vvisit_counterThis week336
mod_vvisit_counterThis month1535
mod_vvisit_counterAll155505

Who's Online

We have 19 guests online

Home Members Ioannis E. Livieris An adaptive nonmonotone active set -weight constrained- neural network training algorithm
Error
  • Error loading feed data.
  • Error loading feed data.
An adaptive nonmonotone active set -weight constrained- neural network training algorithm PDF Print E-mail

I.E. Livieris and P. Pintelas. An adaptive nonmonotone active set -weight constrained- neural network training algorithm. Neurocomputing, 2019

 

 

Abstract - In this work, a new direction for improving the classification accuracy of artificial neural networks is proposed by bounding the weights of the network, during the training process. Furthermore, a new adaptive nonmonotone active set -weight constrainedneural network training algorithm is proposed in order to demonstrate the ecacy and eciency of our approach. The proposed training algorithm consists of two phases: a gradient projection phase which utilizes an adaptive nonmonotone line search and an unconstrained optimization phase which exploits the box structure of the bounds. Also, a set of switching criteria is defined for eciently switching between the two phases. Our preliminary numerical experiments illustrate that the classification efficiency of the proposed algorithm outperforms classical neural network training algorithms, providing empirical evidence that it provides more stable, ecient and reliable learning.

 

Search Engines




bottom
top

Department of Mathematics

Educational Software News

Call for papers

Newest Education Titles


bottom

Designed by Ioannis E. Livieris. | Validate XHTML | CSS