Follow
Mikail Khona
Mikail Khona
PhD candidate, MIT
Verified email at mit.edu - Homepage
Title
Cited by
Cited by
Year
Attractor and integrator networks in the brain
M Khona, IR Fiete
Nature Reviews Neuroscience 23 (12), 744-766, 2022
1302022
No free lunch from deep learning in neuroscience: A case study through models of the entorhinal-hippocampal circuit
R Schaeffer, M Khona, I Fiete
Advances in neural information processing systems 35, 16052-16067, 2022
462022
Reverse-engineering recurrent neural network solutions to a hierarchical inference task for mice
R Schaeffer, M Khona, L Meshulam, IB Laboratory, IR Fiete
Advances in Neural Information Processing Systems 33, 4584-4596, 2020
332020
Double descent demystified: Identifying, interpreting & ablating the sources of a deep learning puzzle
R Schaeffer, M Khona, Z Robertson, A Boopathy, K Pistunova, JW Rocks, ...
arXiv preprint arXiv:2303.14151, 2023
12*2023
From smooth cortical gradients to discrete modules: spontaneous and topologically robust emergence of modularity in grid cells
M Khona, S Chandra, IR Fiete
bioRxiv, 2021.10. 28.466284, 2022
9*2022
Self-supervised learning of representations for space generates multi-modular grid cells
R Schaeffer, M Khona, T Ma, C Eyzaguirre, S Koyejo, I Fiete
Advances in Neural Information Processing Systems 36, 2024
62024
Winning the lottery with neural connectivity constraints: Faster learning across cognitive tasks with spatially constrained sparse rnns
M Khona, S Chandra, JJ Ma, IR Fiete
Neural Computation 35 (11), 1850-1869, 2023
6*2023
Growing brains: Co-emergence of anatomical and functional modularity in recurrent neural networks
Z Liu, M Khona, IR Fiete, M Tegmark
arXiv preprint arXiv:2310.07711, 2023
52023
Efficient online inference for nonparametric mixture models
R Schaeffer, B Bordelon, M Khona, W Pan, IR Fiete
Uncertainty in Artificial Intelligence, 2072-2081, 2021
42021
How capable can a transformer become? a study on synthetic, interpretable tasks
R Ramesh, M Khona, RP Dick, H Tanaka, ES Lubana
arXiv preprint arXiv:2311.12997, 2023
32023
Large language models surpass human experts in predicting neuroscience results
X Luo, A Rechardt, G Sun, KK Nejad, F Yáñez, B Yilmaz, K Lee, ...
arXiv preprint arXiv:2403.03230, 2024
12024
Bridging Associative Memory and Probabilistic Modeling
R Schaeffer, N Zahedi, M Khona, D Pai, S Truong, Y Du, M Ostrow, ...
arXiv preprint arXiv:2402.10202, 2024
1*2024
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
M Khona, M Okawa, J Hula, R Ramesh, K Nishi, R Dick, ES Lubana, ...
arXiv preprint arXiv:2402.07757, 2024
12024
Self-organized emergence of modularity, hierarchy, and mirror reversals from competitive synaptic growth in a developmental model of the visual pathway
S Chandra, M Khona, T Konkle, I Fiete
bioRxiv, 2024.01. 07.574543, 2024
2024
An Information-Theoretic Understanding of Maximum Manifold Capacity Representations
B Isik, V Lecomte, R Schaeffer, Y LeCun, M Khona, R Shwartz-Ziv, ...
UniReps: the First Workshop on Unifying Representations in Neural Models, 2023
2023
Caenorhabditis elegans foraging patterns follow a simple rule of thumb
G Madirolas, A Al-Asmar, L Gaouar, L Marie-Louise, A Garza-Enríquez, ...
Communications Biology 6 (1), 841, 2023
2023
See and Copy: Generation of complex compositional movements from modular and geometric RNN representations
S Duan, M Khona, A Bertagnoli, S Chandra, I Fiete
Proceedings of the 1st NeurIPS Workshop on Symmetry and Geometry in Neural …, 2023
2023
Emergence of robust global modules from local interactions and smooth gradients
M Khona, S Chandra, I Fiete
bioRxiv, 2021.10. 28.466284, 2021
2021
A model for oscillatory gating of information flow between neural circuits as a function of local recurrence
M Khona
Bulletin of the American Physical Society 65, 2020
2020
Towards an Improved Understanding and Utilization of Maximum Manifold Capacity Representations
R Schaeffer, B Isik, DB Pai, A Carranza, V Lecomte, A Unell, M Khona, ...
ICLR 2024 Workshop on Mathematical and Empirical Understanding of Foundation …, 0
The system can't perform the operation now. Try again later.
Articles 1–20