Continual Learning in a Multi-Layer Network of an Electric Fish
Continual Learning in a Multi-Layer Network of an Electric Fish
复制标题
电鱼多层网络中的持续学习
DOI:
10.1016/j.cell.2019.10.020
复制
发表时间:
2019
期刊:
影响因子:
64.5
通讯作者:
Sawtell, Nathaniel B.
中科院分区:
文献类型:
--
作者:
Muller, Salomon Z.;Zadina, Abigail N.;Abbott, L.F.;Sawtell, Nathaniel B.
Distributing learning across multiple layers has proven extremely powerful in artificial neural networks. However, little is known about how multi-layer learning is implemented in the brain. Here, we provide an account of learning across multiple processing layers in the electrosensory lobe (ELL) of mormyrid fish and report how it solves problems well known from machine learning. Because the ELL operates and learns continuously, it must reconcile learning and signaling functions without switching its mode of operation. We show that this is accomplished through a functional compartmentalization within intermediate layer neurons in which inputs driving learning differentially affect dendritic and axonal spikes. We also find that connectivity based on learning rather than sensory response selectivity assures that plasticity at synapses onto intermediate-layer neurons is matched to the requirements of output neurons. The mechanisms we uncover have relevance to learning in the cerebellum, hippocampus, and cerebral cortex, as well as in artificial systems.
登录
查看更多内容
DOI:
10.1523/jneurosci.18-15-06009.1998
发表时间:
1998
期刊:
The Journal of Neuroscience
影响因子:
--
作者:
K. Grant;Y. Sugawara;L. Gómez;Victor Z. Han;C. Bell
通讯作者:
C. Bell
影响因子:
2
作者:
C. Bell;T. Finger;C. J. Russell
通讯作者:
C. J. Russell
影响因子:
2.8
作者:
J. Meek;Kirsty Grant;Curtis C. Bell
通讯作者:
Curtis C. Bell
DOI:
10.1126/science.aaa5694
发表时间:
2016-01-08
期刊:
Science (New York, N.Y.)
影响因子:
--
作者:
Basu J;Zaremba JD;Cheung SK;Hitti FL;Zemelman BV;Losonczy A;Siegelbaum SA
通讯作者:
Siegelbaum SA
影响因子:
--
作者:
V. Hollmann;J. Engelmann;L. Gómez
通讯作者:
L. Gómez