Error-correcting output codes with ensemble diversity for robust learning in neural networks

• Main Authors: Song, Yang, Kang, Qiyu, Tay, Wee Peng
• 其他作者: School of Electrical and Electronic Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2021
• 主題: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Deep Learning; Neural Networks
• 在線閱讀: https://hdl.handle.net/10356/147336
• 機構: Nanyang Technological University

Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications. This paper proposes an error-correcting neural network (ECNN) that combines a set of binary classifiers to combat adversarial exam...