Table of Contents 1. One time setup 1.1 Activation functions 1.2 Data Preprocessing 1.3 Weight Initialization 1.4 Batch Normalization 2. Training dynamics 2.1 Babysitting the Learning Process 2.2 Hype…
Table of Contents 1. One time setup 1.1 Activation functions 1.2 Data Preprocessing 1.3 Weight Initialization 1.4 Batch Normalization 2. Training dynamics 2.1 Babysitting the Learning Process 2.2 Hype…
讨论
登录后参与讨论
还没有评论,来说第一句吧。