Cortical microcircuits as gated-recurrent neural networks

R.P. Costa, Y.M. Assael, B. Shillingford, N. de Freitas, T.P. Vogels, in:, Advances in Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2017, pp. 272–283.

Conference Paper | Published | English
Author
Costa, Rui Ponte; Assael, Yannis M.; Shillingford, Brendan; Freitas, Nando de; Vogels, Tim PIST Austria
Abstract
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.
Publishing Year
Date Published
2017-12-01
Proceedings Title
Advances in Neural Information Processing Systems
Volume
30
Page
272-283
Conference
NIPS: Neural Information Processing System
Conference Location
Long Beach, CA, United States
Conference Date
2017-12-04 – 2017-12-09
ISSN
IST-REx-ID

Cite this

Costa RP, Assael YM, Shillingford B, Freitas N de, Vogels TP. Cortical microcircuits as gated-recurrent neural networks. In: Advances in Neural Information Processing Systems. Vol 30. Neural Information Processing Systems Foundation; 2017:272-283.
Costa, R. P., Assael, Y. M., Shillingford, B., Freitas, N. de, & Vogels, T. P. (2017). Cortical microcircuits as gated-recurrent neural networks. In Advances in Neural Information Processing Systems (Vol. 30, pp. 272–283). Long Beach, CA, United States: Neural Information Processing Systems Foundation.
Costa, Rui Ponte, Yannis M. Assael, Brendan Shillingford, Nando de Freitas, and Tim P Vogels. “Cortical Microcircuits as Gated-Recurrent Neural Networks.” In Advances in Neural Information Processing Systems, 30:272–83. Neural Information Processing Systems Foundation, 2017.
R. P. Costa, Y. M. Assael, B. Shillingford, N. de Freitas, and T. P. Vogels, “Cortical microcircuits as gated-recurrent neural networks,” in Advances in Neural Information Processing Systems, Long Beach, CA, United States, 2017, vol. 30, pp. 272–283.
Costa RP, Assael YM, Shillingford B, Freitas N de, Vogels TP. 2017. Cortical microcircuits as gated-recurrent neural networks. Advances in Neural Information Processing Systems. NIPS: Neural Information Processing System vol. 30. 272–283.
Costa, Rui Ponte, et al. “Cortical Microcircuits as Gated-Recurrent Neural Networks.” Advances in Neural Information Processing Systems, vol. 30, Neural Information Processing Systems Foundation, 2017, pp. 272–83.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data IST Research Explorer

Sources

arXiv 1711.02448

Search this title in

Google Scholar