Training Artificial Neural Networks by Generalized Likelihood Ratio Method: Exploring Brain-like Learning to Improve Robustness
Machine Learning
2019-07-12 v2 Artificial Intelligence
Machine Learning
Abstract
In this work, we propose a generalized likelihood ratio method capable of training the artificial neural networks with some biological brain-like mechanisms,.e.g., (a) learning by the loss value, (b) learning via neurons with discontinuous activation and loss functions. The traditional back propagation method cannot train the artificial neural networks with aforementioned brain-like learning mechanisms. Numerical results show that the robustness of various artificial neural networks trained by the new method is significantly improved when the input data is affected by both the natural noises and adversarial attacks. Code is available: \url{https://github.com/LX-doctorAI/GLR_ADV} .
Cite
@article{arxiv.1902.00358,
title = {Training Artificial Neural Networks by Generalized Likelihood Ratio Method: Exploring Brain-like Learning to Improve Robustness},
author = {Li Xiao and Yijie Peng and Jeff Hong and Zewu Ke and Shuhuai Yang},
journal= {arXiv preprint arXiv:1902.00358},
year = {2019}
}
Comments
12 pages, 7 figures, 2 tables