David Pfau on slow research
There are some papers that go from idea to submission in just a few weeks. Some of my own most-cited papers fall into that category - some were not much more than a few notes that I didn’t even think were worth publishing until someone encouraged me. Our NeurIPS paper this year, "Disentangling by Subspace Diffusion," is not one of those papers. Geoff Hinton said he was working on the idea behind capsule networks for over 17 years before he published anything. The ideas behind this paper have been rattling around in my head for almost as long.
David Pfau On Slow Research There are some papers that go from idea to submission in just a few weeks. Some of my own most-cited papers fall into that category - some were not much more than a few notes that I didn’t even think were worth publishing until someone encouraged me. Our NeurIPS paper this year, " Disentangling by Subspace Diffusion ," is not one of those papers. Geoff Hinton said he was working on the idea behind capsule networks for over 17 years before he published anything. The ideas behind this paper have been rattling around in my head for almost as long. I can trace the first
saved by
related reading
- Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
- A Theory of Deep Learning | Elements of a Vector Spaceelonlit.com
- Distill — Latest articles about machine learningdistill.pub
- The Decade of Deep Learning | Leo Gaobmk.sh
- A History of Large Language Modelsgregorygundersen.com
- Beyond Message Passing: a Physics-Inspired Paradigm for Graph Neural Networksthegradient.pub
- H-Nets - the Past | Goomba Labgoombalab.github.io
- Elon Litman | Elements of a Vector Spaceelonlit.com
- A GPS for the mind | thesephist.comthesephist.com
- Inference, Diffusion, World Models, and More | YC Paper Clubyoutube.com
- Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
- Your Transformer is Secretly an EOT Solver | Elements of a Vector Spaceelonlit.com