팔로우
Akhilan Boopathy
Akhilan Boopathy
mit.edu의 이메일 확인됨
제목
인용
인용
연도
Cnn-cert: An efficient framework for certifying robustness of convolutional neural networks
A Boopathy, TW Weng, PY Chen, S Liu, L Daniel
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 3240-3247, 2019
1712019
PROVEN: Verifying robustness of neural networks with a probabilistic approach
L Weng, PY Chen, L Nguyen, M Squillante, A Boopathy, I Oseledets, ...
International Conference on Machine Learning, 6727-6736, 2019
892019
Proper network interpretability helps adversarial robustness in classification
A Boopathy, S Liu, G Zhang, C Liu, PY Chen, S Chang, L Daniel
International Conference on Machine Learning, 1014-1023, 2020
692020
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
142023
How to train your wide neural network without backprop: An input-weight alignment perspective
A Boopathy, I Fiete
International Conference on Machine Learning, 2178-2205, 2022
72022
Fast training of provably robust neural networks by singleprop
A Boopathy, L Weng, S Liu, PY Chen, G Zhang, L Daniel
Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 6803-6811, 2021
62021
Model-agnostic measure of generalization difficulty
A Boopathy, K Liu, J Hwang, S Ge, A Mohammedsaleh, IR Fiete
International Conference on Machine Learning, 2857-2884, 2023
42023
Interpretability-aware adversarial attack and defense method for deep learnings
S Liu, G Zhang, PY Chen, C Gan, A Boopathy
US Patent 11,397,891, 2022
32022
Divergence at the interpolation threshold: Identifying, interpreting & ablating the sources of a deep learning puzzle
R Schaeffer, Z Robertson, A Boopathy, M Khona, I Fiete, A Gromov, ...
NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning, 2023
22023
Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity
J Hwang, ZW Hong, E Chen, A Boopathy, P Agrawal, I Fiete
arXiv preprint arXiv:2310.17537, 2023
22023
Framework for certifying a lower bound on a robustness level of convolutional neural networks
PY Chen, S Liu, A Boopathy, TW Weng, L Daniel
US Patent 11,625,487, 2023
22023
Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations
A Boopathy, I Fiete
arXiv preprint arXiv:2106.08453, 2021
12021
Visual Interpretability Alone Helps Adversarial Robustness
A Boopathy, S Liu, G Zhang, PY Chen, S Chang, L Daniel
12019
Resampling-free Particle Filters in High-dimensions
A Boopathy, A Muppidi, P Yang, A Iyer, W Yue, I Fiete
arXiv preprint arXiv:2404.13698, 2024
2024
Towards Exact Computation of Inductive Bias
A Boopathy, W Yue, J Hwang, A Iyer, IR Fiete
2023
Breaking Neural Network Scaling Laws with Modularity
A Boopathy, S Jiang, W Yue, J Hwang, A Iyer, IR Fiete
2023
Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building
J Hwang, ZW Hong, ER Chen, A Boopathy, P Agrawal, IR Fiete
2023
Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
R Wang, J Hwang, A Boopathy, IR Fiete
2023
Neuro-Inspired Efficient Map Building via Fragmentation and Recall
J Hwang, ZW Hong, E Chen, A Boopathy, P Agrawal, I Fiete
arXiv preprint arXiv:2307.05793, 2023
2023
Efficient Exploration via Fragmentation and Recall
J Hwang, ZW Hong, ER Chen, A Boopathy, P Agrawal, IR Fiete
2022
현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요.
학술자료 1–20