Completed
Difficulties in Training . Of the two components in the VAE objective, the KL divergence term is much easier to learn
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP - Models with Latent Random Variables
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Discriminative vs. Generative Models
- 3 Quiz: What Types of Variables?
- 4 What is Latent Random Variable Model
- 5 Why Latent Variable Models?
- 6 Deep Structured Latent Variable Models • Specify structure, but interpretable structure is often discrete e.g. POS tags, dependency parse trees
- 7 Examples of Deep Latent Variable Models
- 8 A probabilistic perspective on Variational Auto-Encoder
- 9 What is Our Loss Function?
- 10 Practice
- 11 Variational Inference • Variational inference approximates the true posterior poll with a family of distributions
- 12 Variational Inference • Variational inference approximates the true posterior polar with a family of distributions
- 13 Variational Auto-Encoders
- 14 Variational Autoencoders
- 15 Learning VAE
- 16 Problem! Sampling Breaks Backprop
- 17 Solution: Re-parameterization Trick
- 18 Difficulties in Training . Of the two components in the VAE objective, the KL divergence term is much easier to learn
- 19 Solution 3
- 20 Weaken the Decoder
- 21 Discrete Latent Variables?
- 22 Method 1: Enumeration
- 23 Solution 4
