English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Bounded Rational Decision-Making in Feedforward Neural Networks

Leibfried, F., & Braun, D. (2016). Bounded Rational Decision-Making in Feedforward Neural Networks. In A. Ihler, & D. Janzing (Eds.), Uncertainty in Artificial Intelligence (pp. 407-416). Corvallis, OR, USA: AUAI Press.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0000-7A8E-8 Version Permalink: http://hdl.handle.net/21.11116/0000-0000-7A8F-7
Genre: Conference Paper

Files

show Files

Locators

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

Creators

show
hide
 Creators:
Leibfried, F1, 2, Author              
Braun, D1, 2, 3, Author              
Affiliations:
1Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              
2Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497809              
3Research Group Sensorimotor Learning and Decision-making, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1688138              

Content

show
hide
Free keywords: -
 Abstract: Bounded rational decision-makers transform sensory input into motor output under limited computational resources. Mathematically, such decision-makers can be modeled as information-theoretic channels with limited transmission rate. Here, we apply this formalism for the first time to multilayer feedforward neural networks. We derive synaptic weight update rules for two scenarios, where either each neuron is considered as a bounded rational decision-maker or the network as a whole. In the update rules, bounded rationality translates into information-theoretically motivated types of regularization in weight space. In experiments on the MNIST benchmark classification task for handwritten digits, we show that such information-theoretic regularization successfully prevents overfitting across different architectures and attains results that are competitive with other recent techniques like dropout, dropconnect and Bayes by backprop, for both ordinary and convolutional neural networks.

Details

show
hide
Language(s):
 Dates: 2016-06
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: LeibfriedB2016
 Degree: -

Event

show
hide
Title: 32nd Conference on Uncertainty in Artificial Intelligence (UAI 2016)
Place of Event: New York, NY, USA
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Uncertainty in Artificial Intelligence
Source Genre: Proceedings
 Creator(s):
Ihler , A., Editor
Janzing, D., Editor
Affiliations:
-
Publ. Info: Corvallis, OR, USA : AUAI Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 407 - 416 Identifier: ISBN: 978-0-9966431-1-5