Michael Kleinman
@michaelkleinman
PhD student
ID: 1472645016
http://mjkleinman.github.io 31-05-2013 17:27:31
26 Tweet
95 Takipçi
169 Takip Edilen
Check out our new preprint on using multi-area recurrent neural networks to better understand decision-making. This is joint work with first author Michael Kleinman and co-senior author @ChandMuse. biorxiv.org/content/10.110…
I'm going to be presenting our work on defining a notion of "usable information" and using it to study how optimal representations emerge during NN training! Today at 5pm PDT at ICLR 2021. openreview.net/pdf?id=p8agn6b…. W/ Alessandro Achille, Daksh Idnani, Jonathan Kao
What do LLMs map to in the brain? In some datasets, not much. We emphasize the need for simple controls when analyzing the neural predictivity of trained and untrained LLMs. arxiv.org/abs/2406.01538 In collaboration w/ Ebrahim Feghhi, supervised by I.A.B and Jonathan Kao
1/5 Excited to finally share our new paper (led by Laura Driscoll, now a group leader at the Allen!) in Nature Neuroscience on modular computation in neural networks! We've explored how artificial recurrent networks handle multiple tasks, offering insights into flexible computation.
Excited to share the first paper of my PhD: Towards a theory of learning dynamics in deep state space models arxiv.org/abs/2407.07279 with Jimmy Smith, Michael Kleinman, Dan Biderman, and Scott Linderman. Accepted as a Spotlight talk at the NGSM workshop at ICML 2024!
🌟Announcing NeurIPS spotlight paper on the transition from lazy to rich🔦 We reveal through exact gradient flow dynamics how unbalanced initializations promote rapid feature learning co-led Allan Raventós and Clémentine Dominé, Phd 🍊 FENG CHEN David Klindt Andrew Saxe Surya Ganguli
