Special Session 3

Explainable AI (XAI) in quantum and Neuromorphic Intelligent Systems

This session explores Explainable AI (XAI) methodologies tailored to non-classical computing paradigms—specifically quantum and neuromorphic intelligent systems. It addresses the interpretability of variational quantum circuits, spiking neural networks, and hybrid quantum-neuromorphic architectures, where traditional explanation techniques fail due to superposition, entanglement, and event-driven dynamics. Topics include quantum-aware feature attribution, neuromorphic saliency mapping, causal reasoning in NISQ devices, and trustworthiness metrics for brain-inspired edge intelligence. The session bridges algorithmic transparency with hardware constraints, advancing accountable decision-support, resilient automation, and trustworthy digital ecosystems powered by post-classical AI.

Session Organizers:

Senior Lecturer M. Arvindhan, The American University of Science, Vietnam
Dr. A. Daniel B. E. M. E., MAHE Dubai, UAE

The topics of interest include, but are not limited to:

• XAI for Digital Business and Societal Impact — Governance, regulatory compliance, and socio-technical frameworks for deploying explainable quantum and neuromorphic technologies in digital ecosystems.
• Visualization and Human-AI Interaction — Novel interfaces, quantum state tomography visualizations, and spike-raster explanations for domain experts and non-technical stakeholders.
• Hybrid Quantum-Neuromorphic XAI — Co-design of explanation frameworks across quantum-neuromorphic pipelines, focusing on interface interpretability and cross-paradigm reasoning.
• Energy-Efficient and Hardware-Aware XAI — Lightweight explanation algorithms optimized for constrained quantum and neuromorphic hardware deployments at the edge.
• XAI for Quantum Error Mitigation and Calibration — Explainable diagnostics for error sources, decoder behaviours, and noise profiling in quantum and neuromorphic devices.

Submission Method:

Submit your Full Paper (no less than 4 pages with two colums) or your paper abstract-without publication (200-400 words) via Online Submission System, then choose Special Session 3 (Explainable AI (XAI) in quantum and Neuromorphic Intelligent Systems)
Template Download

Introduction of Session Organizers

Senior Lecturer M. Arvindhan
The American University of Science, Vietnam

Dr. M. Arvindhan is a Senior Lecturer in Computing at The American University of Science, specializing in the intersection of cloud computing, machine learning, and quantum computing. With a portfolio of 89 publications and over 450 citations, his work consistently bridges advanced computational theory with pressing societal and environmental challenges. His unique perspective is shaped by a career dedicated to applying intelligent computing to practical, real-world systems. His collaborative research spans designing AI-driven frameworks for rural hydroponic farming, developing predictive machine learning models for telemedicine, and pioneering carbon-reduction strategies in green cloud data centres. Dedicated to making emerging technologies conceptually accessible. Driven by the potential of digital twins, edge computing, and adaptive resource allocation, Dr. Arvindhan brings a highly pragmatic and forward-looking voice to his field. His commitment to translating complex algorithmic methodologies into sustainable, high-impact technological frameworks makes his expertise an invaluable and timely addition to this series.

Dr. A. Daniel B. E. M. E.
MAHE Dubai, UAE

Dr. A. Daniel B. E. M. E., Ph.D., is a Postdoctoral Researcher with expertise in interdisciplinary scientific research and advanced technological innovation. His research focuses on developing novel methodologies to address complex challenges in his field, with particular interests in emerging technologies, data-driven approaches, and collaborative research. He has contributed to scholarly publications in peer-reviewed journals and international conferences and actively engages in multidisciplinary research collaborations. His academic interests include conducting high-impact research, mentoring students and early-career researchers, and advancing innovative solutions that bridge theoretical foundations with practical applications.