Back to Search
Start Over
Replay in Deep Learning: Current Approaches and Missing Biological Elements
- Source :
- Neural Comput
- Publication Year :
- 2021
- Publisher :
- MIT Press - Journals, 2021.
-
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.<br />Accepted for publication in the MIT Press journal of Neural Computation
- Subjects :
- FOS: Computer and information sciences
Computer Science - Machine Learning
Computer Science - Artificial Intelligence
Computer science
Cognitive Neuroscience
Machine learning
computer.software_genre
Hippocampus
Article
Machine Learning (cs.LG)
Deep Learning
Arts and Humanities (miscellaneous)
Memory formation
Animals
Reinforcement learning
Forgetting
Artificial neural network
business.industry
Deep learning
Mammalian brain
Artificial Intelligence (cs.AI)
FOS: Biological sciences
Quantitative Biology - Neurons and Cognition
Neurons and Cognition (q-bio.NC)
Neural Networks, Computer
Artificial intelligence
Sleep
business
Reinforcement, Psychology
computer
Algorithms
Subjects
Details
- ISSN :
- 1530888X and 08997667
- Database :
- OpenAIRE
- Journal :
- Neural Computation
- Accession number :
- edsair.doi.dedup.....6e0b02a9851000dc72a257d413faaf67