4 papers
Noisy Concurrent Training for Efficient Learning under Label Noise
Fahad Sarfraz, Elahe Arani, Bahram Zonooz
Deep neural networks (DNNs) fail to learn effectively under label noise and have been shown to memorize random labels which affect their generalization performance. We consider lea…
Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks
Elahe Arani, Fahad Sarfraz, Bahram Zonooz
Adversarial training has been proven to be an effective technique for improving the adversarial robustness of models. However, there seems to be an inherent trade-off between optim…
Knowledge Distillation Beyond Model Compression
Fahad Sarfraz, Elahe Arani, Bahram Zonooz
Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretraine…
Reverse engineering neural networks from many partial recordings
Elahe Arani, Sofia Triantafillou, Konrad P. Kording
Much of neuroscience aims at reverse engineering the brain, but we only record a small number of neurons at a time. We do not currently know if reverse engineering the brain requir…