I am a postdoc in CSAIL at MIT advised by Phillip Isola.
My goal is to uncover the computational and statistical laws of natural and artificial intelligence, and thereby design learning systems that are more efficient, more automatic and more useful in practice.
Reach me at jbernstein@mit.edu.
Jeremy Bernstein is a postdoc in CSAIL at MIT advised by Phillip Isola.
His goal is to uncover the computational and statistical laws of natural and artificial intelligence, and thereby design learning systems that are more efficient, more automatic and more useful in practice.
Reach him at jbernstein@mit.edu.
News
- 🪧 Check out my post on deriving the Muon optimizer.
- 🔧 I am continuing to build Modula along with the docs.
- 📝 We posted our paper on modular duality in deep learning.
- 📝 Our optimizer anthology was accepted to the OPT workshop.
- 📝 We presented our paper on the modular norm at NeurIPS.
- 🎥 Video of my talk on metrized deep learning at Cohere.
- 🎓 My PhD thesis is available online.
- 🎥 Video of my talk on neural nets as Bayes Point Machines.