Completed
Glamorous Life of an Al Scientist
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP 2020 - Efficiency Tricks for Neural Nets
Automatically move to the next video in the Classroom when playback concludes
- 1 Glamorous Life of an Al Scientist
- 2 A Simple Example • How long does a matrix-matrix multiply take?
- 3 Practically
- 4 What About Memory?
- 5 Three Types of Parallelism
- 6 Within-operation Parallelism
- 7 Operation-wise Parallelism
- 8 Example-wise Parallelism
- 9 Implementing Data Parallelism • Many modern libraries make data parallelism relatively easy, eg PyTorch DistributedDataParallel
- 10 Computation Across Large Vocabularies
- 11 Noise Contrastive Estimation (Mnih & Teh 2012)
- 12 Mini-batch Based Negative Sampling
- 13 Class-based Softmax (Goodman 2001) • Assign each word to a class • Predict class first, then word given class
- 14 Binary Code Prediction (Dietterich and Bakiri 1995, Oda et al. 2017)
- 15 Two Improvement to Binary Code Prediction
