Talk
in
Workshop: Deep Learning: Bridging Theory and Practice
Contributed Talks 1,2,3,4
[
Abstract
]
2017 Talk
Abstract:
1) Don't Decay the Learning Rate, Increase the Batch Size 2) Meta-Learning and Universality: Deep Representations and Gradient Descent Can Approximate Any Learning Algorithm 3) Hyperparameter Optimization: A Spectral Approach 4) Learning Implicit Generative Models with Method of Learned Moments
Live content is unavailable. Log in and register to view live content