Planned intervention: On Wednesday June 26th 05:30 UTC Zenodo will be unavailable for 10-20 minutes to perform a storage cluster upgrade.

There is a newer version of the record available.

Published July 29, 2023 | Version v1
Conference paper Open

Decentralized Plasticity in Reservoir Dynamical Networks for Pervasive Environments

  • 1. University of Pisa

Description

We propose a framework for localized learning with Reservoir Computing dynamical neural systems in pervasive environments, where data is distributed and dynamic. We use biologically plausible intrinsic plasticity (IP) learning to optimize the non-linearity of system dynamics based on local objectives, and extend it to account for data uncertainty. We develop two algorithms for federated and continual learning, FedIP and FedCLIP, which respectively extend IP to client-server topologies and to prevent catastrophic forgetting in streaming data scenarios. Results on real-world datasets from human monitoring show that our approach improves performance and robustness, while preserving privacy and efficiency. 

Files

fedip_icml_workshop.pdf

Files (5.1 MB)

Name Size Download all
md5:ce04656b9eda124f4c6ff41d6be2f0f1
5.1 MB Preview Download

Additional details

Funding

TEACHING – A computing toolkit for building efficient autonomous applications leveraging humanistic intelligence 871385
European Commission