Performance improvement of in-materio reservoir computing by noise injection
Masaya Hakoshima, Yuki Usami, Takumi Kotooka, Hirofumi Tanaka · Japanese Journal of Applied Physics · 2023
Abstract Computation performance of in-materio reservoir device was evaluated by varying intensity of noise injection. Materials for the reservoir device was synthesized using a α -Fe 2 O 3 /titanium bismuth oxide composite by using the sol–gel method. The prepared samples were characterized by conducting X-ray diffractmetry, transmission electron microscopy, and energy dispersive X-ray spectroscopy to confirm presence of α -Fe 2 O 3 , TiO 2 , and Bi 4 Ti 3 O 12 nanoparticles. The I – V and V – t curves show nonlinearity, and phase differences between input and output signals, and the fast Fourier transform of the V – t curve showed high harmonics at the input sine wave with 11 Hz of frequency. In the waveform prediction task, the prediction accuracy was improved only when a small intensity of white noise voltage was superimposed to the input information signal.