arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1711.02448q-bio.NCcs.NEstat.ML
收藏

作为门控循环神经网络的皮层微回路

Cortical microcircuits as gated-recurrent neural networks

Rui Ponte Costa, Yannis M. Assael, Brendan Shillingford, Nando de Freitas, Tim P. Vogels

摘要:

大脑皮层回路呈现出复杂的循环结构,这些结构在不同的大脑区域之间非常相似。这种刻板的结构表明存在共同的计算原则。然而,这些原则在很大程度上仍然难以实现。受门控记忆网络(即长短期记忆网络(LSTM))的启发,我们引入了一种循环神经网络,其中信息通过减法抑制细胞(subLSTM)进行门控。我们提出了一个自然的映射subLSTM到已知的典型兴奋抑制皮层微电路。我们对序列图像分类和语言建模任务的经验评估表明,subLSTM单元可以实现与LSTM单元相似的性能。这些结果表明,皮层电路可以优化,以解决复杂的上下文问题,并提出了一个新的观点,他们的计算功能。总的来说,我们的工作为统一机器学习中使用的循环网络与其生物对应物迈出了一步。

英文摘要:

Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas. Such stereotyped structure suggests the existence of common computational principles. However, such principles have remained largely elusive. Inspired by gated-memory networks, namely long short-term memory networks (LSTMs), we introduce a recurrent neural network in which information is gated through inhibitory cells that are subtractive (subLSTM). We propose a natural mapping of subLSTMs onto known canonical excitatory-inhibitory cortical microcircuits. Our empirical evaluation across sequential image classification and language modelling tasks shows that subLSTM units can achieve similar performance to LSTM units. These results suggest that cortical circuits can be optimised to solve complex contextual problems and proposes a novel view on their computational function. Overall our work provides a step towards unifying recurrent networks as used in machine learning with their biological counterparts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑