Synaptic metaplasticity in binarized neural networks
Deep neural networks usually rapidly forget the previously learned tasks while training new ones. Laborieux et al. propose a method for training binarized neural networks inspired by neuronal metaplasticity that allows to avoid catastrophic forgetting and is relevant for neuromorphic applications.
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Publishing Group
2021-05-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-021-22768-y |