Structuring Multiple Simple Cycle Reservoirs with Particle Swarm Optimization

2025-04-06

AI Summary

Traditional echo state networks (ESNs) suffer from high reservoir dimensionality and rigid architecture, limiting both efficiency and accuracy in time-series forecasting. To address this, we propose the Multi-Simple-Cycle Reservoir (MSCR) framework: it replaces a single large reservoir with multiple lightweight Simple-Cycle Reservoirs (SCRs) and introduces a learnable, directed acyclic graph (DAG)-based weighted interconnection mechanism to enable task-adaptive topology construction. Furthermore, particle swarm optimization (PSO) is integrated to jointly optimize reservoir parameters and inter-reservoir connection weights. Evaluated on three standard time-series forecasting benchmarks, MSCR achieves superior prediction accuracy compared to state-of-the-art multi-reservoir models—while employing significantly lower state-space dimensionality. The framework thus offers enhanced computational efficiency, architectural flexibility, and improved interpretability through its modular, topology-aware design.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Reservoir Computing (RC) is a time-efficient computational paradigm derived from Recurrent Neural Networks (RNNs). The Simple Cycle Reservoir (SCR) is an RC model that stands out for its minimalistic design, offering extremely low construction complexity and proven capability of universally approximating time-invariant causal fading memory filters, even in the linear dynamics regime. This paper introduces Multiple Simple Cycle Reservoirs (MSCRs), a multi-reservoir framework that extends Echo State Networks (ESNs) by replacing a single large reservoir with multiple interconnected SCRs. We demonstrate that optimizing MSCR using Particle Swarm Optimization (PSO) outperforms existing multi-reservoir models, achieving competitive predictive performance with a lower-dimensional state space. By modeling interconnections as a weighted Directed Acyclic Graph (DAG), our approach enables flexible, task-specific network topology adaptation. Numerical simulations on three benchmark time-series prediction tasks confirm these advantages over rival algorithms. These findings highlight the potential of MSCR-PSO as a promising framework for optimizing multi-reservoir systems, providing a foundation for further advancements and applications of interconnected SCRs for developing efficient AI devices.

Problem

• Optimizing multi-reservoir systems with interconnected Simple Cycle Reservoirs
• Enhancing time-series prediction using Particle Swarm Optimization
• Reducing state space dimensionality while maintaining competitive performance

Innovation

• Multiple interconnected Simple Cycle Reservoirs (MSCRs)
• Particle Swarm Optimization (PSO) for MSCR tuning
• Weighted Directed Acyclic Graph (DAG) interconnections