Learning reservoir dynamics with temporal self-modulation
Abstract Reservoir computing (RC) can efficiently process time-series data by mapping the input signal into a high-dimensional space via randomly connected recurrent neural networks (RNNs), which are referred to as a reservoir. The high-dimensional representation of time-series data in the reservoir...
Main Authors: | Yusuke Sakemi, Sou Nobukawa, Toshitaka Matsuki, Takashi Morie, Kazuyuki Aihara |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-01-01
|
Series: | Communications Physics |
Online Access: | https://doi.org/10.1038/s42005-023-01500-w |
Similar Items
-
Impact of time-history terms on reservoir dynamics and prediction accuracy in echo state networks
by: Yudai Ebato, et al.
Published: (2024-04-01) -
Neural activity responsiveness by maturation of inhibition underlying critical period plasticity
by: Ibuki Matsumoto, et al.
Published: (2025-01-01) -
Model-size reduction for reservoir computing by concatenating internal states through time
by: Yusuke Sakemi, et al.
Published: (2020-12-01) -
Atypical instantaneous spatio-temporal patterns of neural dynamics in Alzheimer’s disease
by: Sou Nobukawa, et al.
Published: (2024-01-01) -
Editorial: Perspectives in brain-network dynamics in computational psychiatry
by: Sou Nobukawa, et al.
Published: (2023-09-01)