Meta-learning biologically plausible plasticity rules with random feedback pathways
The biological plausibility of backpropagation and its relationship with synaptic plasticity remain open questions. The authors propose a meta-learning approach to discover interpretable plasticity rules to train neural networks under biological constraints. The meta-learned rules boost the learning...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-03-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-023-37562-1 |
Summary: | The biological plausibility of backpropagation and its relationship with synaptic plasticity remain open questions. The authors propose a meta-learning approach to discover interpretable plasticity rules to train neural networks under biological constraints. The meta-learned rules boost the learning efficiency via bio-inspired synaptic plasticity. |
---|---|
ISSN: | 2041-1723 |