Replay in deep learning: Current approaches and missing biological elements

Replay in deep learning: Current approaches and missing biological elements

Replay is the reactivation of one or more neural patterns that 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 co...

Full description

Bibliographic Details
Main Authors: Bazhenov, M. (Author), Hayes, T.L (Author), Kanan, C. (Author), Krishnan, G.P (Author), Sejnowski, T.J (Author), Siegelmann, H.T (Author)
Format: Article
Language:English
Published: MIT Press Journals 2021
Subjects:
Activation patterns
algorithm
Algorithms
animal
Animals
Biological neural networks
Catastrophic forgetting
'current
Deep learning
Deep Learning
hippocampus
Hippocampus
Learn+
Learning methods
Mammals
Memory consolidation
Memory formation
Memory retrieval
Neural networks
Neural Networks, Computer
Neural patterns
Reinforcement learning
Reinforcement, Psychology
sleep
Sleep
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items