Free courses from frontend to fullstack and AI
Build the Finance Skills That Lead to Promotions, Not Just Certificates
Overview
Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This lecture examines latent variable models for natural language processing, including variational autoencoders, variational inference, discrete latent variables, reparameterization, sampling, and application examples.
Syllabus
Introduction
Types of Variables
Latent Variable Models
Loss Function
Variational inference
Regularized Autoencoder
Sampling
ancestral sampling
conditioned language models
Motivation for latent variables
Training VAEs
Aggressive inference network learning
Latent variables
Discrete latent variables
Reparameterization
Random Sampling
Reparameterization Trick
Gumball Softmax
Gumball Function
Application Examples
Taught by
Graham Neubig