Home Knowledge Base ESN

ESN

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking

Announce Type: replace Abstract: This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Forecasting Competition dataset. We evaluate whether a simple first-order autoregressive ESN can serve as a competitive alternative to widely used forecasting methods. The study uses a two-stage design: a Parameter dataset is used to analyze ESN model configurations over leakage rate, spectral radius, reservoir...

arXiv CS 8d ago

Linear Reservoir: A Diagonalization-Based Optimization

arXiv:2602.19802v2 Announce Type: replace Abstract: We introduce a diagonalization-based optimization for Linear Echo State Networks (ESNs) that reduces the per-step computational complexity of reservoir state updates from quadratic to linear. By reformulating reservoir dynamics in the eigenbasis of the recurrent matrix, the recurrent update becomes a set of independent element-wise operations, eliminating the matrix multiplication. We further propose three methods to use our optimization...

arXiv CS 7d ago

Fast Linear Reservoirs via Diagonalization

arXiv:2602.19802v3 Announce Type: replace Abstract: We introduce a diagonalization-based optimization for Linear Echo State Networks (ESNs) that reduces the per-step computational complexity of reservoir state updates from quadratic to linear. By reformulating reservoir dynamics in the eigenbasis of the recurrent matrix, the recurrent update becomes a set of independent element-wise operations, eliminating the matrix multiplication. We further propose three methods to use our optimization...

arXiv CS 1d ago

Evolutionary Algorithm for Reservoir Learning and Yielding

arXiv:2605.30372v1 Announce Type: new Abstract: 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...

arXiv CS 9d ago