A deep learning framework for neuroscience.
Journal article

A deep learning framework for neuroscience.

  • Richards BA Mila, Montréal, Quebec, Canada. blake.richards@mcgill.ca.
  • Lillicrap TP DeepMind, Inc., London, UK.
  • Beaudoin P Element AI, Montréal, QC, Canada.
  • Bengio Y Mila, Montréal, Quebec, Canada.
  • Bogacz R MRC Brain Network Dynamics Unit, University of Oxford, Oxford, UK.
  • Christensen A Department of Electrical Engineering, Stanford University, Stanford, CA, USA.
  • Clopath C Department of Bioengineering, Imperial College London, London, UK.
  • Costa RP Computational Neuroscience Unit, School of Computer Science, Electrical and Electronic Engineering, and Engineering Maths, University of Bristol, Bristol, UK.
  • de Berker A Element AI, Montréal, QC, Canada.
  • Ganguli S Department of Applied Physics, Stanford University, Stanford, CA, USA.
  • Gillon CJ Department of Biological Sciences, University of Toronto Scarborough, Toronto, Ontario, Canada.
  • Hafner D Google Brain, Mountain View, CA, USA.
  • Kepecs A Cold Spring Harbor Laboratory, Cold Spring Harbor, NY, USA.
  • Kriegeskorte N Department of Psychology and Neuroscience, Columbia University, New York, NY, USA.
  • Latham P Gatsby Computational Neuroscience Unit, University College London, London, UK.
  • Lindsay GW Zuckerman Mind Brain Behavior Institute, Columbia University, New York, New York, USA.
  • Miller KD Zuckerman Mind Brain Behavior Institute, Columbia University, New York, New York, USA.
  • Naud R University of Ottawa Brain and Mind Institute, Ottawa, Ontario, Canada.
  • Pack CC Department of Neurology & Neurosurgery, McGill University, Montréal, Quebec, Canada.
  • Poirazi P Institute of Molecular Biology and Biotechnology (IMBB), Foundation for Research and Technology-Hellas (FORTH), Heraklion, Crete, Greece.
  • Roelfsema P Department of Vision & Cognition, Netherlands Institute for Neuroscience, Amsterdam, Netherlands.
  • Sacramento J Institute of Neuroinformatics, ETH Zürich and University of Zürich, Zürich, Switzerland.
  • Saxe A Department of Experimental Psychology, University of Oxford, Oxford, UK.
  • Scellier B Mila, Montréal, Quebec, Canada.
  • Schapiro AC Department of Psychology, University of Pennsylvania, Philadelphia, PA, USA.
  • Senn W Department of Physiology, Universität Bern, Bern, Switzerland.
  • Wayne G DeepMind, Inc., London, UK.
  • Yamins D Department of Psychology, Stanford University, Stanford, CA, USA.
  • Zenke F Friedrich Miescher Institute for Biomedical Research, Basel, Switzerland.
  • Zylberberg J Canadian Institute for Advanced Research, Toronto, Ontario, Canada.
  • Therien D Element AI, Montréal, QC, Canada.
  • Kording KP Canadian Institute for Advanced Research, Toronto, Ontario, Canada.
Show more…
  • 2019-10-30
Published in:
  • Nature neuroscience. - 2019
English Systems neuroscience seeks explanations for how the brain implements a wide variety of perceptual, cognitive and motor tasks. Conversely, artificial intelligence attempts to design computational systems based on the tasks they will have to solve. In artificial neural networks, the three components specified by design are the objective functions, the learning rules and the architectures. With the growing success of deep learning, which utilizes brain-inspired architectures, these three designed components have increasingly become central to how we model, engineer and optimize complex artificial learning systems. Here we argue that a greater focus on these components would also benefit systems neuroscience. We give examples of how this optimization-based framework can drive theoretical and experimental progress in neuroscience. We contend that this principled perspective on systems neuroscience will help to generate more rapid progress.
Language
  • English
Open access status
green
Identifiers
Persistent URL
https://folia.unifr.ch/global/documents/52893
Statistics

Document views: 108 File downloads: