Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback

A. Emin Orhan, Wei Ji Ma

Research output: Contribution to journalArticle

Abstract

Animals perform near-optimal probabilistic inference in a wide range of psychophysical tasks. Probabilistic inference requires trial-to-trial representation of the uncertainties associated with task variables and subsequent use of this representation. Previous work has implemented such computations using neural networks with hand-crafted and task-dependent operations. We show that generic neural networks trained with a simple error-based learning rule perform near-optimal probabilistic inference in nine common psychophysical tasks. In a probabilistic categorization task, error-based learning in a generic network simultaneously explains a monkey's learning curve and the evolution of qualitative aspects of its choice behavior. In all tasks, the number of neurons required for a given level of performance grows sublinearly with the input population size, a substantial improvement on previous implementations of probabilistic inference. The trained networks develop a novel sparsity-based probabilistic population code. Our results suggest that probabilistic inference emerges naturally in generic neural networks trained with error-based learning rules.

Original languageEnglish (US)
Article number138
JournalNature communications
Volume8
Issue number1
DOIs
StatePublished - Dec 1 2017

ASJC Scopus subject areas

  • Chemistry(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Physics and Astronomy(all)

Fingerprint Dive into the research topics of 'Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback'. Together they form a unique fingerprint.

  • Cite this