Memristive Explainable Artificial Intelligence Hardware

Abstract

Artificial intelligence (AI) is often considered a black box because it provides optimal answers without clear insight into its decision-making process. To address this black box problem, explainable artificial intelligence (XAI) has emerged, which provides an explanation and interpretation of its decisions, thereby promoting the trustworthiness of AI systems. Here, a memristive XAI hardware framework is presented. This framework incorporates three distinct types of memristors (Mott memristor, valence change memristor, and charge trap memristor), each responsible for performing three essential functions (perturbation, analog multiplication, and integration) required for the XAI hardware implementation. Three memristor arrays with high robustness are fabricated and the image recognition of 3 x 3 testing patterns and their explanation map generation are experimentally demonstrated. Then, a software-based extended system based on the characteristics of this hardware is built, simulating a large-scale image recognition task. The proposed system can perform the XAI operations with only 4.32% of the energy compared to conventional digital systems, enlightening its strong potential for the XAI accelerator. A memristive explainable artificial intelligence (MemXAI) hardware is proposed to provide an explanation and interpretation of AI decisions, where the three essential functions are implemented using three different types of memristors. The MemXAI hardware promotes a trustworthy AI system with low energy consumption of only 4.32% compared to conventional complementary metal-oxide-semiconductor (CMOS)-based computing systems. image