Publication in Chaos

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.

In our newest publication in Chaos, we establish an explicit correspondence between the well-established mathematical RC implementations of Echo State Networks and Band-pass Networks with Leaky Integrator nodes on the one hand and a physical circuit containing iontronic simple volatile memristors on the other. These aqueous iontronic devices employ ion transport through water as signal carriers, and feature a voltage-dependent (memory) conductance. The activation function and the dynamics of the Leaky Integrator nodes naturally materialise as the (dynamic) conductance properties of iontronic memristors, while a simple fixed local current-to-voltage update rule at the memristor terminals facilitates the relevant matrix coupling between nodes. We process various time series, including pressure data from simulated airways during breathing that can be directly fed into the network due to the intrinsic responsiveness of iontronic devices to applied pressures. We accomplish this by employing established physical equations of motion of iontronic memristors for the internal dynamics of the circuit.