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

Behavioural tasks often require probability distributions to be inferred about task specific variables. Here, the authors demonstrate that generic neural networks can be trained using a simple error-based learning rule to perform such probabilistic computations efficiently without any need for task...

Full description

Bibliographic Details
Main Authors: A. Emin Orhan, Wei Ji Ma
Format: Article
Language:English
Published: Nature Portfolio 2017-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-017-00181-8