Suppression of chaos in a partially driven recurrent neural network

no code implementations • 1 Jun 2023 • Shotaro Takasu, Toshio Aoyagi

However, it remains to be theoretically clarified how the restriction of the input to a specific subset of neurons affects the network dynamics.

Use of recurrent infomax to improve the memory capability of input-driven recurrent neural networks

no code implementations • 14 Feb 2018 • Hisashi Iwade, Kohei Nakajima, Takuma Tanaka, Toshio Aoyagi

The inherent transient dynamics of recurrent neural networks (RNNs) have been exploited as a computational resource in input-driven RNNs.