Generative / Discriminative Interface

Generative / Discriminative Interface

9 Lectures · Dec 12, 2009

About

Generative and Discriminative Learning Interface

Generative and discriminative learning are two of the major paradigms for solving prediction problems in machine learning, each offering important distinct advantages. They have often been studied in different sub-communities, but over the past decade, there has been increasing interest in trying to understand and leverage the advantages of both approaches. The goal of this workshop is to map out our current understanding of the empirical and theoretical advantages of each approach as well as their combination, and to identify open research directions.

The aim of this workshop is to provide a platform for both theoretical and applied researchers from different communities to discuss the status of our understanding on the interplay between generative and discriminative learning, as well as to identify forward-looking open problems of interest to the NIPS community. Examples of topics of interest to the workshop are as follows:

* Theoretical analysis of generative vs. discriminative learning
* Techniques for combining generative and discriminative approaches
* Successful applications of hybrids
* Empirical comparison of generative vs. discriminative learning
* Inclusion of prior knowledge in discriminative methods (semi-supervised approaches, generalized expectation criteria, posterior regularization, etc.)
* Insights into the role of generative/discriminative interface for deep learning
* Computational issues in discriminatively trained generative models/hybrid models
* Map of possible generative/discriminative approaches and combinations
* Bayesian approaches optimized for predictive performance
* Comparison of model-free and model-based approaches in statistics or reinforcement learning

The Workshop homepage can be found at http://gen-disc2009.wikidot.com/.

Related categories

Uploaded videos:

video-img
19:31

Opening Address for the NIPS WS on the Generative and Discriminative Learning In...

Mar 26, 2010

 · 

4071 Views

Opening
video-img
34:02

Generative and Discriminative Models in Statistical Parsing

Michael Collins

Mar 26, 2010

 · 

6697 Views

Invited Talk
video-img
18:20

Generative and Discriminative Latent Variable Grammars

Slav Petrov

Mar 26, 2010

 · 

4311 Views

Lecture
video-img
19:03

Discriminative and Generative Views of Binary Experiments

Robert C. Williamson

Mar 26, 2010

 · 

3852 Views

Lecture
video-img
37:24

Multi-Task Discriminative Estimation for Generative Models and Probabilities

Tony Jebara

Mar 26, 2010

 · 

5496 Views

Invited Talk
video-img
29:32

Generative and Discriminative Image Models

John Winn

Mar 26, 2010

 · 

5078 Views

Invited Talk
video-img
21:53

Learning Feature Hierarchies by Learning Deep Generative Models

Ruslan Salakhutdinov

Mar 26, 2010

 · 

6011 Views

Lecture
video-img
22:19

Why Does Unsupervised Pre-training Help Deep Discriminant Learning?

Dumitru Erhan

Mar 26, 2010

 · 

6416 Views

Lecture
video-img
21:32

Unsupervised Learning by Discriminating Data from Artificial Noise

Michael Gutmann

Mar 26, 2010

 · 

4187 Views

Lecture