Computational Principles of Supervised Learning in the Cerebellum.

Computational Principles of Supervised Learning in the Cerebellum.
复制标题

DOI:
10.1146/annurev-neuro-080317-061948
复制
发表时间:
2018-07-08
影响因子:
13.9
通讯作者:
Medina JF
Medina JF
中科院分区:
医学1区
文献类型:
--
作者:
Raymond JL;Medina JF

文献摘要

参考文献

被引文献

相似文献

监督学习在许多生物和人工神经网络的操作中起着关键作用。小脑相对简单和统一的结构促进了对监督学习基础计算的分析,小脑是支持许多运动,感觉和认知功能的大脑区域。我们强调了最近的发现,表明小脑使用以下组织原则实现监督学习:(a)对输入表示进行广泛的预处理(即,特征工程),(B)大规模循环电路结构,(c)线性输入-输出计算,(d)可调节且可预测的复杂指导信号,(e)具有多个时间尺度的可塑性的自适应机制,以及(f)任务特定的硬件专门化。小脑研究中出现的原理与其他大脑区域和人工神经网络中的原理有着惊人的相似之处,也有一些显著的差异,这些差异可以为未来的监督学习研究提供信息,并激发下一代基于机器的算法。
Supervised learning plays a key role in the operation of many biological and artificial neural networks. Analysis of the computations underlying supervised learning is facilitated by the relatively simple and uniform architecture of the cerebellum, a brain area that supports numerous motor, sensory, and cognitive functions. We highlight recent discoveries indicating that the cerebellum implements supervised learning using the following organizational principles: (a) extensive preprocessing of input representations (i.e., feature engineering), (b) massively recurrent circuit architecture, (c) linear input-output computations, (d) sophisticated instructive signals that can be regulated and are predictive, (e) adaptive mechanisms of plasticity with multiple timescales, and (f) task-specific hardware specializations. The principles emerging from studies of the cerebellum have striking parallels with those in other brain areas and in artificial neural networks, as well as some notable differences, which can inform future research on supervised learning and inspire next-generation machine-based algorithms.
DOI: 10.3389/fncir.2012.00091
发表时间: 2012
影响因子: 3.5
作者:
Bazzigaluppi P;De Gruijl JR;van der Giessen RS;Khosrovani S;De Zeeuw CI;de Jeu MT
通讯作者: de Jeu MT
DOI: 10.1038/nn.2195
发表时间: 2008-11
影响因子: 25
作者:
Alvina, Karina;Walter, Joy T.;Kohn, Adam;Ellis-Davies, Graham;Khodakhah, Kamran
通讯作者: Khodakhah, Kamran
DOI: 10.1073/pnas.0808428106
发表时间: 2009-02-17
影响因子: 11.1
作者:
Bengtsson, Fredrik;Jorntell, Henrik
通讯作者: Jorntell, Henrik
DOI: 10.1016/j.neuron.2009.02.022
发表时间: 2009-04-16
期刊: NEURON
影响因子: 16.2
作者:
Carey, Megan R.;Regehr, Wade G.
通讯作者: Regehr, Wade G.
DOI: 10.1038/s41467-017-01109-y
发表时间: 2017-10-24
影响因子: 16.6
作者:
Cayco-Gajic NA;Clopath C;Silver RA
通讯作者: Silver RA