Learning Transformer Programs with Dan Friedman - #667

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

Innhold levert av TWIML and Sam Charrington. Alt podcastinnhold, inkludert episoder, grafikk og podcastbeskrivelser, lastes opp og leveres direkte av TWIML and Sam Charrington eller deres podcastplattformpartner. Hvis du tror at noen bruker det opphavsrettsbeskyttede verket ditt uten din tillatelse, kan du følge prosessen skissert her https://no.player.fm/legal.

1y ago 38:48

MP3•Episoder hjem

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.

743 episoder

#Artificial Intelligence #Tech News #Artificialintelligence #Machinelearning #Samcharrington #Technology #Thisweekinmachinelearning #Sam Charrington #Thetwimlaipocast #Twimlaipodcast #Tech #News #China #TWIML #Datascience #Science