publication . Conference object . Under curation

Continual Learning with Echo State Networks

Andrea Cossu; Davide Bacciu; Antonio Carta; Claudio Gallicchio; Vincenzo Lomonaco;
Open Access English
  • Publisher: Zenodo
Abstract
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.
Persistent Identifiers
Funded by
EC| TEACHING
Project
TEACHING
A computing toolkit for building efficient autonomous applications leveraging humanistic intelligence
  • Funder: European Commission (EC)
  • Project Code: 871385
  • Funding stream: Horizon 2020 Framework Programme - Research and Innovation action
Download from
Open Access
ZENODO
Conference object
Provider: ZENODO
Any information missing or wrong?Report an Issue