Learning Transformer Programs with Dan Friedman - #667

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

TWIML and Sam Charrington에서 제공하는 콘텐츠입니다. 에피소드, 그래픽, 팟캐스트 설명을 포함한 모든 팟캐스트 콘텐츠는 TWIML and Sam Charrington 또는 해당 팟캐스트 플랫폼 파트너가 직접 업로드하고 제공합니다. 누군가가 귀하의 허락 없이 귀하의 저작물을 사용하고 있다고 생각되는 경우 여기에 설명된 절차를 따르실 수 있습니다 https://ko.player.fm/legal.

4M ago 38:48

MP3•에피소드 홈

Today, we continue our NeurIPS series with Dan Friedman, a PhD student in the Princeton NLP group. In our conversation, we explore his research on mechanistic interpretability for transformer models, specifically his paper, Learning Transformer Programs. The LTP paper proposes modifications to the transformer architecture which allow transformer models to be easily converted into human-readable programs, making them inherently interpretable. In our conversation, we compare the approach proposed by this research with prior approaches to understanding the models and their shortcomings. We also dig into the approach’s function and scale limitations and constraints.

The complete show notes for this episode can be found at twimlai.com/go/667.

701 에피소드