Completed
Auto-Sizing Transformer Layers
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Learning Neural Network Hyperparameters for Machine Translation - 2019
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Statistical Machine Translation
- 3 Motivation
- 4 Grid Search
- 5 Method Overview
- 6 Common Regularization
- 7 Objective Function
- 8 Proximal Gradient Methods
- 9 Experiments: 5-gram Language Modeling
- 10 5-gram Perplexity
- 11 Behavior During Training
- 12 Key Takeaways
- 13 Optimal Hyperparameters Not Universal
- 14 Auto-Sizing Transformer Layers
- 15 Pytorch Implementation
- 16 Beam Search
- 17 Perceptron Tuning
- 18 Experiment: Tuned Reward
- 19 Questions?
