What Should a Good Deep Neural Network Look Like? Insights from a Layer-Peeled Model and the Law of Equi-Separation | Stanford Electrical Engineering

Stanford University

What Should a Good Deep Neural Network Look Like? Insights from a Layer-Peeled Model and the Law of Equi-Separation

Sep

28

Wed, Sep 28 2022, 12pm

Prof. Weijie Su (Wharton Statistics and Data Science).
384H