Completed
Learning Domain-invariant Representations (Ganin et al. 2016) • Learn features that cannot be distinguished by domain
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP 2017 - Adversarial Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Generative Models
- 3 Adversarial Training
- 4 Basic Paradigm
- 5 Problems with Generation • Over-emphasis of common outputs, fuzziness Adversarial
- 6 Training Method
- 7 In Equations
- 8 Problems w/ Training
- 9 Applications of GAN Objectives to Language
- 10 Problem! Can't Backprop through Sampling
- 11 Solution: Use Learning Methods for Latent Variables
- 12 Discriminators for Sequences
- 13 Stabilization Trick
- 14 Interesting Application: GAN for Data Cleaning (Yang et al. 2017)
- 15 Adversaries over Features vs. Over Outputs
- 16 Learning Domain-invariant Representations (Ganin et al. 2016) • Learn features that cannot be distinguished by domain
- 17 Adversarial Multi-task Learning (Liu et al. 2017)
- 18 Implicit Discourse Connection Classification w/ Adversarial Objective
- 19 Professor Forcing (Lamb et al. 2016)
- 20 Unsupervised Style Transfer for Text (Shen et al. 2017)
