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
Explore this link on the map →related reading
- An Opinionated Guide to ML Researchjoschu.net
- A Survival Guide to a PhDkarpathy.github.io
- Research Debtdistill.pub
- How to win a best paper award (or, an opinionated take on how to do important research)nicholas.carlini.com
- Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
- Neural Networks, Manifolds, and Topology -- colah's blogcolah.github.io
- On Really Trying · Gwern.netgwern.net
- Home - colah's blogcolah.github.io
- Work hard | What's newterrytao.wordpress.com
- Just know stuff. (Or, how to achieve success in a machine learning PhD.) · Patrick Kidgerkidger.site
- Zen and the Art of Machine Learning Researchblog.jxmo.io
- Interpretability Dreamstransformer-circuits.pub