
Episode 07: Yujia Huang, Caltech, on neuro-inspired generative models
Generally Intelligent
00:00
How to Use Generative Models to Help Classification
I got very interested in the idea of using generative models to help classification. It's actually a pretty old idea. Maybe this back to 2002 and to end public paper saying generative classifiers can learn more efficiently than discriminated classifiers. In point of view, I think it makes sense because you try to get a global sense of the data distribution rather than trying to memorize which one is better.
Transcript
Play full episode