Unsupervised Learning in Echo State Networks for Input Reconstruction
Abstract
Conventional echo state networks (ESNs) require supervised learning to train the readout layer, using the desired outputs as training data. In this study, we focus on input reconstruction (IR), which refers to training the readout layer to reproduce the input time series in its output. We reformulate the learning algorithm of the ESN readout layer to perform IR using unsupervised learning (UL). By conducting theoretical analysis and numerical experiments, we demonstrate that IR in ESNs can be effectively implemented under realistic conditions without explicitly using the desired outputs as training data; in this way, UL is enabled. Furthermore, we demonstrate that applications relying on IR, such as dynamical system replication and noise filtering, can be reformulated within the UL framework. Our findings establish a theoretically sound and universally applicable IR formulation, along with its related tasks in ESNs. This work paves the way for novel predictions and highlights unresolved theoretical challenges in ESNs, particularly in the context of time-series processing methods and computational models of the brain.
- Publication:
-
arXiv e-prints
- Pub Date:
- January 2025
- arXiv:
- arXiv:2501.11409
- Bibcode:
- 2025arXiv250111409Y
- Keywords:
-
- Computer Science - Machine Learning;
- Computer Science - Artificial Intelligence;
- Electrical Engineering and Systems Science - Signal Processing;
- Nonlinear Sciences - Chaotic Dynamics;
- Quantitative Biology - Neurons and Cognition
- E-Print:
- 16 pages, 7 figures, regular paper