no code implementations • 5 Dec 2019 • Hanten Chang, Katsuya Futagami
The RCRC model uses a fixed random-weight CNN and a reservoir computing model to extract visual and time-series features.
no code implementations • 2 Dec 2019 • Hiroyasu Ando, Hanten Chang
Reservoir computing derived from recurrent neural networks is more applicable to real world systems than deep learning because of its low computational cost and potential for physical implementation.
1 code implementation • 18 Jul 2019 • Hanten Chang, Katsuya Futagami
Many of these models collect considerable data on the tasks and improve accuracy by extracting visual and time-series features using convolutional neural networks (CNNs) and recurrent neural networks, respectively.
no code implementations • 22 May 2019 • Hanten Chang, Shinji Nakaoka, Hiroyasu Ando
We investigate prediction accuracy for time series of Echo state networks with respect to several kinds of activation functions.