top
logo

Login Form



Visitors Counter

mod_vvisit_counterToday30
mod_vvisit_counterYesterday52
mod_vvisit_counterThis week331
mod_vvisit_counterThis month1530
mod_vvisit_counterAll155501

Who's Online

We have 8 guests online

Home Members Ioannis E. Livieris Improving the classification efficiency of an ANN utilizing a new training methodology
Error
  • Error loading feed data.
  • Error loading feed data.
Improving the classification efficiency of an ANN utilizing a new training methodology PDF Print E-mail

I.E. Livieris. Improving the classification efficiency of an ANN utilizing a new training methodology. Informatics, 2018.

 

 

Abstract - In this work, a new approach for training artificial neural networks is presented which utilizes techniques for solving the constraint optimization problem. More specifically, this study converts the training of a neural network into a constraint optimization problem. Furthermore, we propose a new neural network training algorithm based on L-BFGS-B method. Our numerical experiments illustrate the classification efficiency of the proposed algorithm and of our proposed methodology, leading to more efficient, stable and robust predictive models.

 

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