A deep learning framework for neuroscience
File(s)
Accepted version
Author(s)
Type
Journal Article
Abstract
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 the case of artificial neural networks, the three components specified by design are the objective functions, the learning rules, and 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.
Date Issued
2019-11-01
Date Acceptance
2019-09-23
Citation
Nature Neuroscience, 2019, 22 (11), pp.1761-1770
ISSN
1097-6256
Publisher
Nature Research
Start Page
1761
End Page
1770
Journal / Book Title
Nature Neuroscience
Volume
22
Issue
11
Copyright Statement
© 2019 Springer Nature America, Inc.
Sponsor
Wellcome Trust
Biotechnology and Biological Sciences Research Council (BBSRC)
Biotechnology and Biological Sciences Research Cou
Simons Foundation
National Institutes of Health
Grant Number
200790/Z/16/Z
BB/P018785/1
ORCA 64155 (BB/N013956/1)
Award ID:564408
18-AO-00-1001392
Subjects
1109 Neurosciences
1702 Cognitive Sciences
1701 Psychology
Neurology & Neurosurgery
Publication Status
Published
Date Publish Online
2019-10-28