Urmăriți
Ben Sorscher
Ben Sorscher
Adresă de e-mail confirmată pe stanford.edu
Titlu
Citat de
Citat de
Anul
Beyond neural scaling laws: beating power law scaling via data pruning
B Sorscher*, R Geirhos*, S Shekhar, S Ganguli, A Morcos
Advances in Neural Information Processing Systems 35, 19523-19536, 2022
3702022
A unified theory for the computational and mechanistic origins of grid cells
B Sorscher*, GC Mel*, SA Ocko, LM Giocomo, S Ganguli
Neuron 111 (1), 121-137. e13, 2023
912023
A unified theory for the origin of grid cells through the lens of pattern formation
B Sorscher*, G Mel*, S Ganguli, SA Ocko
Advances in Neural Information Processing Systems 32, 2019
772019
Neural representational geometry underlies few-shot concept learning
B Sorscher, S Ganguli, H Sompolinsky
Proceedings of the National Academy of Sciences 119 (43), e2200800119, 2022
712022
Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks
A Nayebi, A Attinger, M Campbell, K Hardcastle, I Low, CS Mallory, G Mel, ...
Advances in Neural Information Processing Systems 34, 12167-12179, 2021
372021
One-shot entorhinal maps enable flexible navigation in novel environments
JH Wen*, B Sorscher*, EA Aery Jones, S Ganguli, LM Giocomo
Nature, 1-8, 2024
92024
Representations and generalization in artificial and brain neural networks
Q Li, B Sorscher, H Sompolinsky
Proceedings of the National Academy of Sciences 121 (27), e2311805121, 2024
72024
When and why grid cells appear or not in trained path integrators
B Sorscher, GC Mel, A Nayebi, L Giocomo, D Yamins, S Ganguli
bioRxiv, 2022.11. 14.516537, 2022
52022
A theory of weight distribution-constrained learning
W Zhong, B Sorscher, D Lee, H Sompolinsky
Advances in Neural Information Processing Systems 35, 14113-14127, 2022
32022
A theory of learning with constrained weight-distribution
W Zhong, B Sorscher, DD Lee, H Sompolinsky
arXiv preprint arXiv:2206.08933, 2022
22022
Statistical mechanics of deep learning
F Behrens, N Mainali, C Marullo, S Lee, B Sorscher, H Sompolinsky
Journal of Statistical Mechanics: Theory and Experiment 2024 (10), 104007, 2024
2024
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–11