Alert button
Picture for Akhilan Boopathy

Akhilan Boopathy

Alert button

Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity

Oct 26, 2023
Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete

Viaarxiv icon

Neuro-Inspired Efficient Map Building via Fragmentation and Recall

Jul 11, 2023
Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete

Figure 1 for Neuro-Inspired Efficient Map Building via Fragmentation and Recall
Figure 2 for Neuro-Inspired Efficient Map Building via Fragmentation and Recall
Figure 3 for Neuro-Inspired Efficient Map Building via Fragmentation and Recall
Figure 4 for Neuro-Inspired Efficient Map Building via Fragmentation and Recall
Viaarxiv icon

Model-agnostic Measure of Generalization Difficulty

May 01, 2023
Akhilan Boopathy, Kevin Liu, Jaedong Hwang, Shu Ge, Asaad Mohammedsaleh, Ila Fiete

Figure 1 for Model-agnostic Measure of Generalization Difficulty
Figure 2 for Model-agnostic Measure of Generalization Difficulty
Figure 3 for Model-agnostic Measure of Generalization Difficulty
Figure 4 for Model-agnostic Measure of Generalization Difficulty
Viaarxiv icon

Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle

Mar 24, 2023
Rylan Schaeffer, Mikail Khona, Zachary Robertson, Akhilan Boopathy, Kateryna Pistunova, Jason W. Rocks, Ila Rani Fiete, Oluwasanmi Koyejo

Figure 1 for Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
Figure 2 for Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
Figure 3 for Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
Figure 4 for Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
Viaarxiv icon

Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations

Jun 15, 2021
Akhilan Boopathy, Ila Fiete

Figure 1 for Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations
Figure 2 for Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations
Figure 3 for Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations
Figure 4 for Gradient-trained Weights in Wide Neural Networks Align Layerwise to Error-scaled Input Correlations
Viaarxiv icon

Fast Training of Provably Robust Neural Networks by SingleProp

Feb 01, 2021
Akhilan Boopathy, Tsui-Wei Weng, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Luca Daniel

Figure 1 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 2 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 3 for Fast Training of Provably Robust Neural Networks by SingleProp
Figure 4 for Fast Training of Provably Robust Neural Networks by SingleProp
Viaarxiv icon

Proper Network Interpretability Helps Adversarial Robustness in Classification

Jun 26, 2020
Akhilan Boopathy, Sijia Liu, Gaoyuan Zhang, Cynthia Liu, Pin-Yu Chen, Shiyu Chang, Luca Daniel

Figure 1 for Proper Network Interpretability Helps Adversarial Robustness in Classification
Figure 2 for Proper Network Interpretability Helps Adversarial Robustness in Classification
Figure 3 for Proper Network Interpretability Helps Adversarial Robustness in Classification
Figure 4 for Proper Network Interpretability Helps Adversarial Robustness in Classification
Viaarxiv icon

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks

Nov 29, 2018
Akhilan Boopathy, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel

Figure 1 for CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Figure 2 for CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Figure 3 for CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Figure 4 for CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
Viaarxiv icon