Training Artificial Neural Networks by Generalized Likelihood Ratio Method: Exploring Brain-like Learning to Improve Robustness

Authors: Li Xiao, Yijie Peng, Jeff Hong, Zewu Ke, Shuhuai Yang
Published: 2019-01-31 | Updated: 2019-07-11

Source: https://arxiv.org/abs/1902.00358

PDF: https://arxiv.org/pdf/1902.00358

AIにより推定されたラベル

損失項 最適化問題 ロバスト性向上

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

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: https://github.com/LX-doctorAI/GLR_ADV .