[3줄 AutoML] 옵티마이저도 한번 찾아볼까?

https://arxiv.org/abs/1709.07417 Neural Optimizer Search with Reinforcement Learning We present an approach to automate the process of discovering optimization methods, with a focus on deep learning architectures. We train a Recurrent Neural Network controller to generate a string in a domain specific language that describes a mathematical arxiv.org 1. 뉴럴넷도 찾고, 활성화함수도 찾는데 옵티마이저라고 못 찾을 거 있나? 옵티마이..

2021.07.07