Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Matsuki, Toshitaka"'
Chaos-based reinforcement learning (CBRL) is a method in which the agent's internal chaotic dynamics drives exploration. This approach offers a model for considering how the biological brain can create variability in its behavior and learn in an expl
Externí odkaz:
http://arxiv.org/abs/2405.09086
Reservoir computing (RC) can efficiently process time-series data by transferring the input signal to randomly connected recurrent neural networks (RNNs), which are referred to as a reservoir. The high-dimensional representation of time-series data i
Externí odkaz:
http://arxiv.org/abs/2301.09235
Autor:
Matsuki, Toshitaka
Recurrent neural network (RNN) based reinforcement learning (RL) is used for learning context-dependent tasks and has also attracted attention as a method with remarkable learning performance in recent research. However, RNN-based RL has some issues
Externí odkaz:
http://arxiv.org/abs/2203.01465
Publikováno v:
Neural Networks, vol.143, pp.436-451 (2021)
Here, we introduce a fully local index named "sensitivity" for each neuron to control chaoticity or gradient globally in a neural network (NN). We also propose a learning method to adjust it named "sensitivity adjustment learning (SAL)". The index is
Externí odkaz:
http://arxiv.org/abs/2012.13134
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Neural Networks November 2021 143:436-451
Autor:
Matsuki, Toshitaka, Shibata, Katsunari
Publikováno v:
In Neural Networks December 2020 132:19-29
Autor:
Matsuki, Toshitaka, Shibata, Katsunari
Publikováno v:
Neural Information Processing: 23rd International Conference, ICONIP 2016, Kyoto, Japan, October 16-21, 2016, Proceedings, Part I; 2016, p376-383, 8p