7-Methylquinolinium Iodobismuthate Memristor: Exploring Plasticity and Memristive Properties for Digit Classification in Physical Reservoir Computing

Abstract

This study investigates 7-methylquinolinium halobismuthates (I, Br, and Cl) in two aspects: (1) their structural and semiconducting properties influenced by anionic composition, and (2) their memristive and plasticity characteristics for neuromorphic and reservoir computing applications. Structural changes induced by halides form low-dimensional halobismuthate fragments, confirmed by crystallographic analysis. Optical band gaps were studied using diffuse reflectance spectroscopy, aligning with density functional theory results. Due to solubility limitations, only bismuth iodide complexes were explored in electronic devices. Current-voltage scans showed pinched hysteresis loops, characteristic of memristors. Conductivity versus temperature study indicates combined ionic and electronic contributions to conductivity of the devices. Given that a memristor can function as a single synapse without the need for programming, aligning with the requirements of neuromorphic computing, the study investigated long-term depression, potentiation, and spike-time-dependent plasticity. As the potentiation-depression plots showed non-linearity with fading memory, these materials can be a good candidate for application in physical reservoir computing. To further assess this material, an electronic device with sixteen gold electrodes was applied, featuring one input and 15 output electrodes deposited on silicon substrate and covered with a layer of studied compound. Basic test to assess the complexity and non-linearity of the devices were conducted through a series of benchmark tasks, including waveform generation, NARMA-2, memory capacity assessment, and noise study under both DC and AC current. The ability of device in MNIST digit classification with 82.26% accuracy and voice classification for digit 2 for six different people with 82 % accuracy has been demonstrated.