Physical recurrent neural networks within a brain-inspired substrate

What is it about?

Reservoir computing (RC) is a proven method for processing temporal data and has drawn more recent attention as a suitable framework for hardware based machine learning. Echo State and Band-pass Networks are extensively studied implementations of RC. We propose a novel physical circuit design, based on fluidic iontronic memristors, that provides a one-to-one correspondence with the mathematical descriptions of these RC paradigms. Using the underlying equations of motion of these fluidic devices, we process several time series, including simulated respiratory pressure waveforms, exploiting iontronics’ intrinsic sensitivity to applied pressures. Our direct physical (iontronic) realization of these established RC implementations offers a blueprint for physically embedded temporal processing with an emerging substrate.

Featured Image

Photo by Sandip Kalal on Unsplash

Photo by Sandip Kalal on Unsplash