Batch normalization
One of the biggest turning points in making deep networks trainable. The idea is one sentence, the effect is enormous.
2 steps
110 XP
A free account is needed
Start the lesson →
Sources
- Ioffe, S. & Szegedy, C. 2015 · Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift · ICML 2015
- Santurkar, S. et al. 2018 · How Does Batch Normalization Help Optimization? · NeurIPS 2018
- Ba, Kiros, Hinton 2016 · Layer Normalization · arXiv:1607.06450
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons