Biologically inspired sleep algorithm for increased generalization and adversarial robustness in deep neural networks

no code implementations • ICLR 2020 • Timothy Tadros, Giri Krishnan, Ramyaa Ramyaa, Maxim Bazhenov

In this work, we utilize a biologically inspired sleep phase in ANNs and demonstrate the benefit of sleep on defending against adversarial attacks as well as in increasing ANN classification robustness.

Adversarial Robustness General Classification +2

Biologically inspired sleep algorithm for artificial neural networks

no code implementations • 1 Aug 2019 • Giri P. Krishnan, Timothy Tadros, Ramyaa Ramyaa, Maxim Bazhenov

First, in an incremental learning framework, sleep is able to recover older tasks that were otherwise forgotten in the ANN without sleep phase due to catastrophic forgetting.

Incremental Learning Transfer Learning