Conference paper Open Access
Continual Learning with Echo State Networks
Andrea Cossu; Davide Bacciu; Antonio Carta; Claudio Gallicchio; Vincenzo Lomonaco
Continual Learning (CL) refers to a learning setup where
data is non stationary and the model has to learn without forgetting ex-
isting knowledge. The study of CL for sequential patterns revolves around
trained recurrent networks. In this work, instead, we introduce CL in the
context of Echo State Networks (ESNs), where the recurrent component
is kept fixed. We provide the first evaluation of catastrophic forgetting in
ESNs and we highlight the benefits in using CL strategies which are not
applicable to trained recurrent models. Our results confirm the ESN as a
promising model for CL and open to its use in streaming scenarios.
| All versions | This version | |
|---|---|---|
| Views | 73 | 73 |
| Downloads | 70 | 70 |
| Data volume | 8.7 MB | 8.7 MB |
| Unique views | 67 | 67 |
| Unique downloads | 66 | 66 |
- Publication date:
- August 5, 2021
- DOI:
-
- Keyword(s):
- continual learning; echo state networks; recurrent neural networks
- Grants:
-
European Commission:
- TEACHING - A computing toolkit for building efficient autonomous applications leveraging humanistic intelligence (871385)
- Meeting:
- European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International