---
_id: '8129'
abstract:
- lang: eng
  text: "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.\r\nOverall our work provides a step towards unifying recurrent networks
    as used in machine learning with their biological counterparts."
article_processing_charge: No
arxiv: 1
author:
- first_name: Rui Ponte
  full_name: Costa, Rui Ponte
  last_name: Costa
- first_name: Yannis M.
  full_name: Assael, Yannis M.
  last_name: Assael
- first_name: Brendan
  full_name: Shillingford, Brendan
  last_name: Shillingford
- first_name: Nando de
  full_name: Freitas, Nando de
  last_name: Freitas
- first_name: Tim P
  full_name: Vogels, Tim P
  id: CB6FF8D2-008F-11EA-8E08-2637E6697425
  last_name: Vogels
  orcid: 0000-0003-3295-6181
citation:
  ama: 'Costa RP, Assael YM, Shillingford B, Freitas N de, Vogels TP. Cortical microcircuits
    as gated-recurrent neural networks. In: <i>Advances in Neural Information Processing
    Systems</i>. Vol 30. Neural Information Processing Systems Foundation; 2017:272-283.'
  apa: 'Costa, R. P., Assael, Y. M., Shillingford, B., Freitas, N. de, &#38; Vogels,
    T. P. (2017). Cortical microcircuits as gated-recurrent neural networks. In <i>Advances
    in Neural Information Processing Systems</i> (Vol. 30, pp. 272–283). Long Beach,
    CA, United States: Neural Information Processing Systems Foundation.'
  chicago: Costa, Rui Ponte, Yannis M. Assael, Brendan Shillingford, Nando de Freitas,
    and Tim P Vogels. “Cortical Microcircuits as Gated-Recurrent Neural Networks.”
    In <i>Advances in Neural Information Processing Systems</i>, 30:272–83. Neural
    Information Processing Systems Foundation, 2017.
  ieee: R. P. Costa, Y. M. Assael, B. Shillingford, N. de Freitas, and T. P. Vogels,
    “Cortical microcircuits as gated-recurrent neural networks,” in <i>Advances in
    Neural Information Processing Systems</i>, Long Beach, CA, United States, 2017,
    vol. 30, pp. 272–283.
  ista: '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.'
  mla: Costa, Rui Ponte, et al. “Cortical Microcircuits as Gated-Recurrent Neural
    Networks.” <i>Advances in Neural Information Processing Systems</i>, vol. 30,
    Neural Information Processing Systems Foundation, 2017, pp. 272–83.
  short: 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:
  end_date: 2017-12-09
  location: Long Beach, CA, United States
  name: 'NIPS: Neural Information Processing System'
  start_date: 2017-12-04
date_created: 2020-07-16T19:13:10Z
date_published: 2017-12-01T00:00:00Z
date_updated: 2025-06-26T10:30:43Z
day: '01'
extern: '1'
external_id:
  arxiv:
  - '1711.02448'
intvolume: '        30'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://arxiv.org/abs/1711.02448
month: '12'
oa: 1
oa_version: Preprint
page: 272-283
publication: Advances in Neural Information Processing Systems
publication_identifier:
  issn:
  - '10495258'
publication_status: published
publisher: Neural Information Processing Systems Foundation
quality_controlled: '1'
status: public
title: Cortical microcircuits as gated-recurrent neural networks
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 30
year: '2017'
...