Replay as a Basis for Backpropagation Through Time in the Brain

How episodic memories are formed in the brain is a continuing puzzle for the neuroscience community. The brain areas that are critical for episodic learning (e.g., the hippocampus) are characterized by recurrent connectivity and generate frequent offline replay events. The function of the replay eve...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neural computation Ročník 37; číslo 3; s. 403
Hlavní autori: Cheng, Huzi, Brown, Joshua W
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States 14.02.2025
Predmet:
Algorithms
Animals
Brain - physiology
Computer Simulation
Hippocampus - physiology
Humans
Learning - physiology
Memory, Episodic
Models, Neurological
Neural Networks, Computer
Rats
Time Factors
ISSN:1530-888X, 1530-888X
On-line prístup:Zistit podrobnosti o prístupe
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:How episodic memories are formed in the brain is a continuing puzzle for the neuroscience community. The brain areas that are critical for episodic learning (e.g., the hippocampus) are characterized by recurrent connectivity and generate frequent offline replay events. The function of the replay events is a subject of active debate. Recurrent connectivity, computational simulations show, enables sequence learning when combined with a suitable learning algorithm such as backpropagation through time (BPTT). BPTT, however, is not biologically plausible. We describe here, for the first time, a biologically plausible variant of BPTT in a reversible recurrent neural network, R2N2, that critically leverages offline replay to support episodic learning. The model uses forward and backward offline replay to transfer information between two recurrent neural networks, a cache and a consolidator, that perform rapid one-shot learning and statistical learning, respectively. Unlike replay in standard BPTT, this architecture requires no artificial external memory store. This approach outperforms existing solutions like random feedback local online learning and reservoir network. It also accounts for the functional significance of hippocampal replay events. We demonstrate the R2N2 network properties using benchmark tests from computer science and simulate the rodent delayed alternation T-maze task.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1530-888X
1530-888X
DOI:10.1162/neco_a_01735