Asymptotic evaluation of the information processing capacity in reservoir computing

📅 2025-02-15
🏛️ arXiv.org
📈 Citations: 1
Influential: 0
📄 PDF
🤖 AI Summary
Existing methods for estimating the information processing capacity (IPC) of reservoir computing (RC) systems lack theoretical rigor and suffer from systematic bias when applied to infinitely long time series, as they rely exclusively on finite-length data. Method: This paper proposes a novel IPC estimation algorithm based on asymptotic expansion and least-squares estimation. It establishes, for the first time, a rigorous asymptotic expansion framework for IPC in the infinite-time limit, integrating stochastic dynamical systems modeling, asymptotic analysis, and least-squares regression to analytically characterize and efficiently estimate the leading-order term of IPC. Results: Numerical experiments demonstrate consistently high accuracy and strong generalizability across diverse RC architectures—including echo state networks (ESNs) and liquid state machines (LSMs)—thereby significantly enhancing the reliability and theoretical soundness of long-term performance evaluation.

Technology Category

Application Category

📝 Abstract
The squared error normalized by the target output is known as the information processing capacity (IPC) and is used to evaluate the performance of reservoir computing (RC). Since RC aims to learn the relationship between input and output time series, we should evaluate the IPC for infinitely long data rather than the IPC for finite-length data. To evaluate the IPC for infinitely long data using the IPC for finite-length data, we use an asymptotic expansion of the IPC and the least-squares method. Then, we show the validity of our method by numerical simulations.
Problem

Research questions and friction points this paper is trying to address.

Evaluating information processing capacity for infinite data in reservoir computing
Establishing method to estimate asymptotic performance of RC systems
Validating new evaluation approach through numerical simulations
Innovation

Methods, ideas, or system contributions that make the work stand out.

Used asymptotic expansion of IPC
Applied weighted least-squares fitting
Validated method through numerical simulations
💼 Related Jobs
No related jobs found.
Y
Yohei Saito
Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology