This Friday 18-06-2021, 5.30pm CEST, for the ContinualAI Reading Group, Tyler Hayes will present the paper:
Abstract: Replay is the reactivation of one or more neural patterns, which are similar to the activation patterns experienced during past waking experiences. Replay was first observed in biological neural networks during sleep, and it is now thought to play a critical role in memory formation, retrieval, and consolidation. Replay-like mechanisms have been incorporated into deep artificial neural networks that learn over time to avoid catastrophic forgetting of previous knowledge. Replay algorithms have been successfully used in a wide range of deep learning methods within supervised, unsupervised, and reinforcement learning paradigms. In this paper, we provide the first comprehensive comparison between replay in the mammalian brain and replay in artificial neural networks. We identify multiple aspects of biological replay that are missing in deep learning systems and hypothesize how they could be utilized to improve artificial neural networks.
The event will be moderated by: Vincenzo Lomonaco
Eventbrite event: Eventbrite Link
Microsoft Teams: click here to join
Slides: Hayes_Replay_Talk_June_2021.pdf - Google Drive
Video: ContinualAI RG: “Replay in Deep Learning: Current Approaches and Missing Biological Elements” - YouTube
Looking forward to seeing you all there!