Adversarial Explanations
Walt discusses the concept of adversarial explanations and how they can improve the robustness and generalizability of classification networks. He explains that the noise patterns in adversarial examples indicate biases in the dataset, highlighting the need for more effective robustness techniques. Walt also provides information on where to find the code and how to get in touch with him for further discussion.In this clip
From this podcast
Data Skeptic
Adversarial Explanations
Related Questions