Title: AI, Innovation and Global Transformation: Interdisciplinary Perspectives on Technology, Business and Society
Editors: Dr. J. Preetha, and Dr. Siddhartha Mehrotra
ISBN: 978-81-69857-64-2
Chapter: 27
DOI: https://doi.org/10.59646/809/27
Authors: Prof. Prakash Shankar Andhare, Prof. Pankaj Ramdas Bhusari, Prof. Patil Jyoti Kamalakar, and Prof. Prashant Sopan Ingale
Abstract
Quantum Machine Learning (QML) represents a disruptive computational paradigm situated at the nexus of quantum information theory and statistical learning. As contemporary classical artificial intelligence grapples with non-polynomial optimization landscapes, intractable multidimensional feature domains, and unsustainable computational power demands, QML leverages fundamental quantum mechanical phenomena—namely coherence, superposition, entanglement, and quantum tunneling—to process information within exponentially expanded Hilbert spaces. This chapter provides a rigorous investigation into parameter-efficient hybrid quantum-classical algorithms, evaluating Parameterized Quantum Circuits (PQCs), Variational Quantum Classifiers (VQCs), and Quantum Neural Networks (QNNs). Through formal mathematical modeling and empirical simulation, we demonstrate how high-dimensional state embedding bypasses classical curse-of-dimensionality constraints. Systematic benchmarks establish comparative performance across accuracy, empirical convergence rates, computational runtime scaling, and resilience against barren plateaus under varying quantum circuit depths and gate-noise regimes. The chapter culminates in an actionable evaluation framework establishing design foundations for next-generation quantum-accelerated artificial intelligence architectures.
Keywords: Quantum Machine Learning; Variational Quantum Circuits; Quantum Neural Networks; Barren Plateaus; Parameterized Quantum Circuits; Quantum Advantage.