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

28 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Replay in Deep Learning: Current Approaches and Missing Biological Elements (2021, neutral): “Furthermore, Tadros, Krishnan, Ramyaa, & Bazhenov (2020a, 2020b) and Krishnan, Tadros, Ramyaa, and Bazhenov (2019) However, many replay algorithms still differ from how humans learn and assimilate new information.”
Biological underpinnings for lifelong learning machines (2022, methodology): “Mechanisms such as neuromodulation 78,158,199 , multisensory integration 113,162 , hierarchical distributed systems 113,191 , reconfigurable organisms 139,147 and episodic replay 176,177 have been used to help improve the noise tolerance of L2 systems.”
Advances in adversarial attacks and defenses in computer vision: A survey (2021, background): “A concept of biologically inspired post-learning sleep phase of neural networks was introduced in [382].”