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...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2017-07-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-017-00181-8 |