English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Deep Neural Networks: A New Tool for Understanding the Brain

Bethge, M., & Brendel, W. (2016). Deep Neural Networks: A New Tool for Understanding the Brain. Talk presented at Satellite Workshop "Deep Neural Networks": Bernstein Conference 2016. Berlin, Germany.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0000-7C4A-3 Version Permalink: http://hdl.handle.net/21.11116/0000-0000-DD6C-F
Genre: Talk

Files

show Files

Locators

show
hide
Locator:
Link (Any fulltext)
Description:
-

Creators

show
hide
 Creators:
Bethge, M1, 2, Author              
Brendel, W, Author
Affiliations:
1Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              
2Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805              

Content

show
hide
Free keywords: -
 Abstract: Today, machine learning is developing ever more complex artificial neural networks that are becoming increasingly proficient in mimicking the perceptual inference abilities of humans and animals. This progress sparks many exciting opportunities for Computational Neuroscience. The most basic application is to use deep learning as a tool for fitting data. More generally, however, functionally impressive deep neural networks can be understood as novel model systems that join and extend the range of biological model systems (e.g. fly, rodent, or monkey) studied today. These artificial model systems are particularly useful to study the relation between structure and function, because the full connectome and responses of all neurons are readily available, and the absence of experimental limitations triggers new questions on what it takes to understand neural networks. Deep neural networks can also be used as ground truth models to better assess what conclusions can be drawn from neurophysiological experiments by simulating the experiments under the same limitations we face for biological model systems. The goal of this workshop is to elaborate on these broad ideas by sharing recent successes in using deep neural networks, exchanging new approaches, and sparking discussions on how we can use the potential of recent advances in artificial neural network modeling for computational neuroscience.

Details

show
hide
Language(s):
 Dates: 2016-09-21
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: BethgeB2016
 Degree: -

Event

show
hide
Title: Satellite Workshop "Deep Neural Networks": Bernstein Conference 2016
Place of Event: Berlin, Germany
Start-/End Date: -
Invited: Yes

Legal Case

show

Project information

show

Source 1

show
hide
Title: Satellite Workshop "Deep Neural Networks": Bernstein Conference 2016
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -