---
_id: '9633'
abstract:
- lang: eng
  text: The search for biologically faithful synaptic plasticity rules has resulted
    in a large body of models. They are usually inspired by – and fitted to – experimental
    data, but they rarely produce neural dynamics that serve complex functions. These
    failures suggest that current plasticity models are still under-constrained by
    existing data. Here, we present an alternative approach that uses meta-learning
    to discover plausible synaptic plasticity rules. Instead of experimental data,
    the rules are constrained by the functions they implement and the structure they
    are meant to produce. Briefly, we parameterize synaptic plasticity rules by a
    Volterra expansion and then use supervised learning methods (gradient descent
    or evolutionary strategies) to minimize a problem-dependent loss function that
    quantifies how effectively a candidate plasticity rule transforms an initially
    random network into one with the desired function. We first validate our approach
    by re-discovering previously described plasticity rules, starting at the single-neuron
    level and “Oja’s rule”, a simple Hebbian plasticity rule that captures the direction
    of most variability of inputs to a neuron (i.e., the first principal component).
    We expand the problem to the network level and ask the framework to find Oja’s
    rule together with an anti-Hebbian rule such that an initially random two-layer
    firing-rate network will recover several principal components of the input space
    after learning. Next, we move to networks of integrate-and-fire neurons with plastic
    inhibitory afferents. We train for rules that achieve a target firing rate by
    countering tuned excitation. Our algorithm discovers a specific subset of the
    manifold of rules that can solve this task. Our work is a proof of principle of
    an automated and unbiased approach to unveil synaptic plasticity rules that obey
    biological constraints and can solve complex functions.
acknowledgement: We would like to thank Chaitanya Chintaluri, Georgia Christodoulou,
  Bill Podlaski and Merima Šabanovic for useful discussions and comments. This work
  was supported by a Wellcome Trust ´ Senior Research Fellowship (214316/Z/18/Z),
  a BBSRC grant (BB/N019512/1), an ERC consolidator Grant (SYNAPSEEK), a Leverhulme
  Trust Project Grant (RPG-2016-446), and funding from École Polytechnique, Paris.
article_processing_charge: No
author:
- first_name: Basile J
  full_name: Confavreux, Basile J
  id: C7610134-B532-11EA-BD9F-F5753DDC885E
  last_name: Confavreux
- first_name: Friedemann
  full_name: Zenke, Friedemann
  last_name: Zenke
- first_name: Everton J.
  full_name: Agnes, Everton J.
  last_name: Agnes
- first_name: Timothy
  full_name: Lillicrap, Timothy
  last_name: Lillicrap
- 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: 'Confavreux BJ, Zenke F, Agnes EJ, Lillicrap T, Vogels TP. A meta-learning
    approach to (re)discover plasticity rules that carve a desired function into a
    neural network. In: <i>Advances in Neural Information Processing Systems</i>.
    Vol 33. ; 2020:16398-16408.'
  apa: Confavreux, B. J., Zenke, F., Agnes, E. J., Lillicrap, T., &#38; Vogels, T.
    P. (2020). A meta-learning approach to (re)discover plasticity rules that carve
    a desired function into a neural network. In <i>Advances in Neural Information
    Processing Systems</i> (Vol. 33, pp. 16398–16408). Vancouver, Canada.
  chicago: Confavreux, Basile J, Friedemann Zenke, Everton J. Agnes, Timothy Lillicrap,
    and Tim P Vogels. “A Meta-Learning Approach to (Re)Discover Plasticity Rules That
    Carve a Desired Function into a Neural Network.” In <i>Advances in Neural Information
    Processing Systems</i>, 33:16398–408, 2020.
  ieee: B. J. Confavreux, F. Zenke, E. J. Agnes, T. Lillicrap, and T. P. Vogels, “A
    meta-learning approach to (re)discover plasticity rules that carve a desired function
    into a neural network,” in <i>Advances in Neural Information Processing Systems</i>,
    Vancouver, Canada, 2020, vol. 33, pp. 16398–16408.
  ista: 'Confavreux BJ, Zenke F, Agnes EJ, Lillicrap T, Vogels TP. 2020. A meta-learning
    approach to (re)discover plasticity rules that carve a desired function into a
    neural network. Advances in Neural Information Processing Systems. NeurIPS: Conference
    on Neural Information Processing Systems vol. 33, 16398–16408.'
  mla: Confavreux, Basile J., et al. “A Meta-Learning Approach to (Re)Discover Plasticity
    Rules That Carve a Desired Function into a Neural Network.” <i>Advances in Neural
    Information Processing Systems</i>, vol. 33, 2020, pp. 16398–408.
  short: B.J. Confavreux, F. Zenke, E.J. Agnes, T. Lillicrap, T.P. Vogels, in:, Advances
    in Neural Information Processing Systems, 2020, pp. 16398–16408.
conference:
  end_date: 2020-12-12
  location: Vancouver, Canada
  name: 'NeurIPS: Conference on Neural Information Processing Systems'
  start_date: 2020-12-06
date_created: 2021-07-04T22:01:27Z
date_published: 2020-12-06T00:00:00Z
date_updated: 2023-10-18T09:20:55Z
day: '06'
department:
- _id: TiVo
ec_funded: 1
intvolume: '        33'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://proceedings.neurips.cc/paper/2020/hash/bdbd5ebfde4934142c8a88e7a3796cd5-Abstract.html
month: '12'
oa: 1
oa_version: Published Version
page: 16398-16408
project:
- _id: c084a126-5a5b-11eb-8a69-d75314a70a87
  grant_number: 214316/Z/18/Z
  name: What’s in a memory? Spatiotemporal dynamics in strongly coupled recurrent
    neuronal networks.
- _id: 0aacfa84-070f-11eb-9043-d7eb2c709234
  call_identifier: H2020
  grant_number: '819603'
  name: Learning the shape of synaptic plasticity rules for neuronal architectures
    and function through machine learning.
publication: Advances in Neural Information Processing Systems
publication_identifier:
  issn:
  - 1049-5258
publication_status: published
quality_controlled: '1'
related_material:
  link:
  - relation: is_continued_by
    url: https://doi.org/10.1101/2020.10.24.353409
  record:
  - id: '14422'
    relation: dissertation_contains
    status: public
scopus_import: '1'
status: public
title: A meta-learning approach to (re)discover plasticity rules that carve a desired
  function into a neural network
type: conference
user_id: 6785fbc1-c503-11eb-8a32-93094b40e1cf
volume: 33
year: '2020'
...