top
logo

Login Form



Visitors Counter

mod_vvisit_counterToday36
mod_vvisit_counterYesterday52
mod_vvisit_counterThis week337
mod_vvisit_counterThis month1536
mod_vvisit_counterAll155507

Who's Online

We have 23 guests online

Home Members Ioannis E. Livieris An advanced active set L-BFGS algorithm for training constrained neural networks
Error
  • Error loading feed data.
  • Error loading feed data.
An advanced active set L-BFGS algorithm for training constrained neural networks PDF Print E-mail

I.E. Livieris. An advanced active set L-BFGS algorithm for training constrained neural networks. Neural Computing and its Applications, 2019.

 

 

Abstract - In this work, a new advanced active set limited memory BFGS (Broyden–Fletcher–Goldfarb–Shanno) algorithm is proposed for efficiently training weight-constrained neural networks, called AA-L-BFGS. The proposed algorithm possesses the significant property of approximating the curvature of the error function with high-order accuracy by utilizing the {\color{blue}theoretically advantaged} secant condition. Moreover, the global convergence of the proposed algorithm is established provided that the line search satisfies the modified Armijo condition. The presented numerical experiments illustrate the efficiency of the proposed AA-L-BFGS, providing empirical evidence that it significantly accelerates the convergence of the training process.

 

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