David Bau: Interpretation of Deep Networks

I am an Assistant Professor of Computer Science at Northeastern Khoury College. My lab studies the structure and interpretation of deep networks. We think that understanding the rich internal structure of deep networks is a grand and fundamental research question with many practical implications. We aim to lay the groundwork for human-AI collaborative software engineering, where humans and machine-learned models both teach and learn from each other. Want to come to Boston to work on deep learning with me? Apply to Khoury here and contact me if you are interested in joining as a graduate student or postdoc. Also check out NDIF engineering fellowships. Publication List. (PNAS; NeurIPS; ICLR; TPAMI; CVPR; SIGGRAPH; ECCV; ICCV.) Curriculum Vitae. (PhD MIT EECS, thesis; Cornell; Harvard; Google; Microsoft. Sloan fellowship, Spira teaching award) Publication pages on Dblp and Google Scholar. Talks at the Bau Lab ; What is AI interpretability for? Sheridan Feucht Nikhil Prakash Rohit Gandi

David Bau: Interpretation of Deep Networks David Bau Knowing What Neural Networks Know Northeastern University Khoury College of Computer Sciences Massachusetts Institute of Technology --> New! The Aletheia's Quest AI lie-detection contest from Cadenza Labs and NDIF is now underway - see the current leaderboard . David Bau (center) and family: (clockwise) Heidi, Cody, Piper, and Anthony --> --> Why we study deep network internals. David Bau (narrates), with Antonio Torralba, Jun-Yan Zhu, Hendrik Strobelt, Jonas Wulff, and William Peebles. Video by Lillie Paquette, MIT School of Engineering. --

related reading

• Transformer Circuits Threadtransformer-circuits.pub
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• The Building Blocks of Interpretabilitydistill.pub
• GenAI Handbookgenai-handbook.github.io
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• The Decade of Deep Learning | Leo Gaobmk.sh
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• The World Inside Neural Networksgoodfire.ai
• Structure and Interpretation of Deep Networkssidn.baulab.info
• Interpretability Dreamstransformer-circuits.pub
• Neuronpedianeuronpedia.org
• Interpretability — LessWronglesswrong.com