Episode · Nov 3, 2017
Learning to Learn, and other Opportunities in Machine Learning
The TWIML AI Podcast
We use cookies for analytics.
Podcast, The TWIML AI Podcast
Hosted by Sam Charrington
Hugo Larochelle discusses using intermediate representations to improve transfer and composing features for few-shot image classification. The episode also covers zero-shot language-model prompting and the use of repository-level information to adapt code-completion prompts.