Imperial College London
Alternate

Professor Claudia Clopath

Faculty of Engineering, Department of Bioengineering

Professor of Computational Neuroscience
 
 
 
//

Contact

 

+44 (0)20 7594 1435c.clopath Website

 
 
//

Location

 

Royal School of Mines 4.09Royal School of MinesSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Richards:2019:10.1038/s41593-019-0520-2,
author = {Richards, BA and Lillicrap, TP and Beaudoin, P and Bengio, Y and Bogacz, R and Christensen, A and Clopath, C and Costa, RP and de, Berker A and Ganguli, S and Gillon, CJ and Hafner, D and Kepecs, A and Kriegeskorte, N and Latham, P and Lindsay, GW and Naud, R and Pack, CC and Poirazi, P and Roelfsema, P and Sacramento, J and Saxe, A and Scellier, B and Schapiro, A and Senn, W and Greg, W and Yamins, D and Zenke, F and Zylberberg, J and Therien, D and Kording, KP},
doi = {10.1038/s41593-019-0520-2},
journal = {Nature Neuroscience},
pages = {1761--1770},
title = {A deep learning framework for neuroscience},
url = {http://dx.doi.org/10.1038/s41593-019-0520-2},
volume = {22},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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.
AU  - Richards,BA
AU  - Lillicrap,TP
AU  - Beaudoin,P
AU  - Bengio,Y
AU  - Bogacz,R
AU  - Christensen,A
AU  - Clopath,C
AU  - Costa,RP
AU  - de,Berker A
AU  - Ganguli,S
AU  - Gillon,CJ
AU  - Hafner,D
AU  - Kepecs,A
AU  - Kriegeskorte,N
AU  - Latham,P
AU  - Lindsay,GW
AU  - Naud,R
AU  - Pack,CC
AU  - Poirazi,P
AU  - Roelfsema,P
AU  - Sacramento,J
AU  - Saxe,A
AU  - Scellier,B
AU  - Schapiro,A
AU  - Senn,W
AU  - Greg,W
AU  - Yamins,D
AU  - Zenke,F
AU  - Zylberberg,J
AU  - Therien,D
AU  - Kording,KP
DO  - 10.1038/s41593-019-0520-2
EP  - 1770
PY  - 2019///
SN  - 1097-6256
SP  - 1761
TI  - A deep learning framework for neuroscience
T2  - Nature Neuroscience
UR  - http://dx.doi.org/10.1038/s41593-019-0520-2
UR  - http://hdl.handle.net/10044/1/74212
VL  - 22
ER  -
Download