Competitive Cross-Entropy Loss: A Study on Training Single-Layer Neural Networks for Solving Nonlinearly Separable Classification Problems

This page is designed to help the researchers to repeat the experiments of the following publication:

K. Ghiasi-Shirazi. Competitive Cross-Entropy Loss: A Study on Training Single-Layer Neural Networks for Solving Nonlinearly Separable Classification Problems. Neural Processing Letters, Volume 50, Issue 2, pp 1115-1122, October 2019. (post-peer-review, pre-copyedit version) , (final authenticated version)

Datasets

All datasets can be downloaded from here.
Small-size datasets are also available from here.

Software

The code of this paper can obtained from here.
You can convert the downloaded datasets to appropriate formats by using this conversion code.