Statistical temperature coefficient distribution in analog RRAM array: impact on neuromorphic system and mitigation method

Abstract

Emerging analog resistive random access memory (RRAM) based on HfOx is an attractive device for non-von Neumann neuromorphic computing systems. The differences in temperature dependent conductance drift among cells hamper computing accuracy, characterized by the statistical distribution of temperature coefficient(Tα). A compact model was presented in order to investigate the statistical distribution of Tα under different resistance states. Based on this model, the physical mechanism of thermal instability of cells with a positive Tα was elucidated. Furthermore, this model can also effectively evaluate the impact of conductance distribution of different levels under various temperatures in artificial neural networks (ANN). An approach incorporating the optimized conductance range selection and the current compensation scheme was proposed to reduce the impacts of the distribution of Tα. The simulation results showed that recognition accuracy was improved from 79.8% to 89.6% for the application of MNIST handwriting digits classification with a two-layer perceptron at 400K after adopting the proposed optimization method.

Advancement in Soft Iontronic Resistive Memory Devices and Their Application for Neuromorphic Computing

“…[75,76,101,107] To understand the working mechanism, liquid materials as an active switching medium or liquid electrodes are introduced, which help to understand the filament formation using the ion concentration polarization phenomena with the movement of anion and cation resulting in oxidation and reduction on the active metal electrode, which results in electrochemical metallization. [79,[90][91][92] External factors are utilized to modulate resistive switching behavior, which directs effects on the device filament formation and ion movement in an active layer, which is based on temperature, [108][109][110] light, [111,112] and humidity. [113][114][115] In recent, few works have been reported to modulate switching behavior using the ionic liquid, which results in modulation in resistive memory behavior.…”