Advances in computational intelligence and robotics book series
Quantum Explainable AI
Tushar Tushar, Pooja Jaiswal, Shyam Sundar
Abstract
Quantum Explainable Artificial Intelligence (QXAI) is an interdisciplinary and rapidly developing branch of quantum computing that integrates the concepts of XAI with the principles of quantum computing, to make hybrid quantum-classical systems more transparent, reliable, and interpretable. In this chapter the principles of QXAI are derived from quantum information theory, entropy, fidelity analysis and computational complexity modeling. It introduces the QuXAI framework and the Q-MEDLEY explainer to provide feature attribution for hybrid quantum-classical machine learning models and maintain quantum transformations. The chapter explores a more in-depth analysis of noisy quantum states with the help of entropy and fidelity analysis and quantum simulation, noise modeling, and fuzzy c means clustering. Moreover, it presents interpretable quantum-inspired models, such as QIIM and TNIM, and proposes the Quantum Attention Network to facilitate the analysis of quantum complexity in the era of AI-enhanced quantum intelligent systems, scaling up and making them transparent and responsible.