Replay in Deep Learning: Current Approaches and Missing Biological Elements.
Replay in Deep Learning: Current Approaches and Missing Biological Elements.
复制标题
DOI:
10.1162/neco_a_01433
复制
发表时间:
2021-10-12
影响因子:
2.9
通讯作者:
Kanan, Christopher
中科院分区:
文献类型:
--
作者:
Hayes, Tyler L.;Krishnan, Giri P.;Bazhenov, Maxim;Siegelmann, Hava T.;Sejnowski, Terrence J.;Kanan, Christopher
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.
登录
查看更多内容
影响因子:
5.7
作者:
Bader, Regine;Mecklinger, Axel;Meyer, Patric
通讯作者:
Meyer, Patric
DOI:
10.1016/s0764-4469(97)82472-9
发表时间:
1997-12-01
期刊:
COMPTES RENDUS DE L ACADEMIE DES SCIENCES SERIE III-SCIENCES DE LA VIE-LIFE SCIENCES
影响因子:
--
作者:
Ans, B;Rousset, S
通讯作者:
Rousset, S
影响因子:
4.8
作者:
Barakat, Marc;Carrier, Julie;Doyon, Julien
通讯作者:
Doyon, Julien
影响因子:
16.2
作者:
Aimone JB;Deng W;Gage FH
通讯作者:
Gage FH
影响因子:
8.2
作者:
Baird, Benjamin;Smallwood, Jonathan;Schooler, Jonathan W.
通讯作者:
Schooler, Jonathan W.