Learning Reservoir Dynamics with Temporal Self-Modulation

no code implementations • 23 Jan 2023 • Yusuke Sakemi, Sou Nobukawa, Toshitaka Matsuki, Takashi Morie, Kazuyuki Aihara

In this paper, to improve the learning ability of RC, we propose self-modulated RC (SM-RC), which extends RC by adding a self-modulation mechanism.

Time Series Time Series Analysis

Deep Q-network using reservoir computing with multi-layered readout

no code implementations • 3 Mar 2022 • Toshitaka Matsuki

This paper shows that the performance of this method improves by using a multi-layered neural network for the readout layer, which regularly consists of a single linear layer.

Reinforcement Learning (RL) Time Series +1

Sensitivity -- Local Index to Control Chaoticity or Gradient Globally

no code implementations • 24 Dec 2020 • Katsunari Shibata, Takuya Ejima, Yuki Tokumaru, Toshitaka Matsuki

We also propose a learning method to adjust it named "sensitivity adjustment learning (SAL)".