Enregistré dans:
Détails bibliographiques
Auteurs principaux: Testu, Julien, Legrand, Pierrick, Hinaut, Xavier
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.30372
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914614787178496
author Testu, Julien
Legrand, Pierrick
Hinaut, Xavier
author_facet Testu, Julien
Legrand, Pierrick
Hinaut, Xavier
contents Reservoir computing, a type of recurrent neural network, is a promising approach for temporal learning as it separates dynamic processing from the trained readout layer. However, classical Echo State Networks (ESNs) often require task-specific tuning of their architecture and hyperparameters to achieve good performance. This paper introduces EARLY (Evolutionary Algorithm for Reservoir Learning and Yielding), a framework designed to evolve both the topology and hyperparameters of multi-reservoir ESNs. Inspired by the modular organisation of the brain, EARLY encodes architectures as graph-based genomes and applies crossover, mutation, and selection to discover effective configurations. Our goal is to create both generic architectures and tasks inducing generalization. The method is evaluated on temporal learning tasks from the CogScale dataset. Results show that evolved architectures outperform those obtained with random search on several tasks and exhibit structural differences depending on task difficulty: simpler tasks yield lightweight architectures, while more complex tasks favour richer modular organisations. These findings suggest that evolutionary search can help identify reusable reservoir structures for a broader range of temporal problems. The evolved architectures are further evaluated on a cross-situational learning dataset to assess their ability to adapt to new environments.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30372
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evolutionary Algorithm for Reservoir Learning and Yielding
Testu, Julien
Legrand, Pierrick
Hinaut, Xavier
Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
Neurons and Cognition
Reservoir computing, a type of recurrent neural network, is a promising approach for temporal learning as it separates dynamic processing from the trained readout layer. However, classical Echo State Networks (ESNs) often require task-specific tuning of their architecture and hyperparameters to achieve good performance. This paper introduces EARLY (Evolutionary Algorithm for Reservoir Learning and Yielding), a framework designed to evolve both the topology and hyperparameters of multi-reservoir ESNs. Inspired by the modular organisation of the brain, EARLY encodes architectures as graph-based genomes and applies crossover, mutation, and selection to discover effective configurations. Our goal is to create both generic architectures and tasks inducing generalization. The method is evaluated on temporal learning tasks from the CogScale dataset. Results show that evolved architectures outperform those obtained with random search on several tasks and exhibit structural differences depending on task difficulty: simpler tasks yield lightweight architectures, while more complex tasks favour richer modular organisations. These findings suggest that evolutionary search can help identify reusable reservoir structures for a broader range of temporal problems. The evolved architectures are further evaluated on a cross-situational learning dataset to assess their ability to adapt to new environments.
title Evolutionary Algorithm for Reservoir Learning and Yielding
topic Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
Neurons and Cognition
url https://arxiv.org/abs/2605.30372