A more biologically plausible learning rule for neural networks

Pietro Mazzoni, Richard A. Andersen, Michael I. Jordan

Research output: Contribution to journalArticlepeer-review

122 Scopus citations

Abstract

Many recent studies have used artificial neural network algorithms to model how the brain might process information. However, back-propagation learning, the method that is generally used to train these networks, is distinctly "unbiological." We describe here a more biologically plausible learning rule, using reinforcement learning, which we have applied to the problem of how area 7a in the posterior parietal cortex of monkeys might represent visual space in head-centered coordinates. The network behaves similarly to networks trained by using back-propagation and to neurons recorded in area 7a. These results show that a neural network does not require back propagation to acquire biologically interesting properties.

Original languageEnglish
Pages (from-to)4433-4437
Number of pages5
JournalProceedings of the National Academy of Sciences of the United States of America
Volume88
Issue number10
DOIs
StatePublished - May 15 1991
Externally publishedYes

Keywords

  • Coordinate transformation
  • Hebbian synapses
  • Posterior parietal cortex
  • Reinforcement learning
  • Sensorimotor integration

Fingerprint Dive into the research topics of 'A more biologically plausible learning rule for neural networks'. Together they form a unique fingerprint.

Cite this