Projects per year
Fingerprint
Dive into the research topics where Boris Hanin is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Collaborations and top research areas from the last five years
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
-
Career: Random Neural Nets and Random Matrix Products
Hanin, B. (PI)
NSF - National Science Foundation
6/1/22 → 5/31/27
Project: Research project
-
Collaborative Research: Probabilistic, Geometric, and Topological Analysis of Neural Networks, From Theory to Applications
Hanin, B. (PI)
NSF - National Science Foundation
1/1/22 → 12/31/24
Project: Research project
-
Random Neural Networks
Hanin, B. (PI)
NSF - National Science Foundation
8/1/20 → 5/31/23
Project: Research project
-
DEPTHWISE HYPERPARAMETER TRANSFER IN RESIDUAL NETWORKS: DYNAMICS AND SCALING LIMIT
Bordelon, B., Noci, L., Li, M., Hanin, B. & Pehlevan, C., 2024.Research output: Contribution to conference › Paper › peer-review
1 Scopus citations -
PRINCIPLED ARCHITECTURE-AWARE SCALING OF HYPERPARAMETERS
Chen, W., Wu, J., Wang, Z. & Hanin, B., 2024.Research output: Contribution to conference › Paper › peer-review
-
Bayesian interpolation with deep linear networks
Hanin, B. & Zlokapa, A., Jun 2023, In: Proceedings of the National Academy of Sciences of the United States of America. 120, 23, e2301345120.Research output: Contribution to journal › Article › peer-review
Open Access8 Scopus citations -
Maximal Initial Learning Rates in Deep ReLU Networks
Iyer, G., Hanin, B. & Rolnick, D., 2023, In: Proceedings of Machine Learning Research. 202, p. 14500-14530 31 p.Research output: Contribution to journal › Conference article › peer-review
3 Scopus citations -
RANDOM NEURAL NETWORKS IN THE INFINITE WIDTH LIMIT AS GAUSSIAN PROCESSES
Hanin, B., Dec 2023, In: Annals of Applied Probability. 33, 6A, p. 4798-4819 22 p.Research output: Contribution to journal › Article › peer-review
4 Scopus citations