Interpretability for Reliable, Efficient, and Self-Cognitive DNNs: from Theories to Applications.
NEUROCOMPUTING（2023）
关键词
Deep Neural Networks,Interpretability,Explainability,Adversarial attacks,Attribution,Information geometry,Causality
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要