Downloads: 0
Research Paper | Computer Science and Information Technology | Volume 11 Issue 8, August 2022 | Pages: 1596 - 1607 | United States
Quantum-Inspired Optimisation for Large-Scale Artificial Intelligence: A Critical Comparative Review of Algorithms, Scalability, and Practical Applicability
Abstract: The increasing complexity of artificial intelligence (AI) has created a need for effective optimisation of highdimensional, nonlinear, and computationally expensive problems. Quantum-inspired optimisation provides an alternative approach by employing quantum-inspired representations and search mechanisms within classical computing systems. This review examines major approaches, including Quantum-Inspired Evolutionary Algorithms (QIEA), Quantum-Inspired Genetic Algorithms (QIGA), Quantum-Inspired Particle Swarm Optimisation (QIPSO), quantum annealing-related approaches, and hybrid methods. Their applications in machine learning, feature selection, hyperparameter optimisation, reinforcement learning, healthcare, finance, cybersecurity, robotics, and smart manufacturing are reviewed. Particular emphasis is placed on solution quality, convergence behaviour, computational cost, scalability, robustness, and reproducibility. The review identifies inconsistent benchmarking, parameter sensitivity, computational overhead, and limited reproducibility as major challenges. The findings indicate that quantum-inspired optimisation should not be considered universally superior to classical optimisation, as its effectiveness depends on problem structure and evaluation conditions. Future research should focus on scalable, hybrid, explainable, and reproducible optimisation frameworks for realistic large-scale AI applications.
Keywords: Artificial Intelligence, Quantum-Inspired Algorithms, Quantum Computing, Optimisation, Machine Learning, Quantum Annealing, Evolutionary Algorithms, Large-Scale Optimisation
How to Cite?: Rajesh Palthya, "Quantum-Inspired Optimisation for Large-Scale Artificial Intelligence: A Critical Comparative Review of Algorithms, Scalability, and Practical Applicability", Volume 11 Issue 8, August 2022, International Journal of Science and Research (IJSR), Pages: 1596-1607, https://www.ijsr.net/getabstract.php?paperid=SR22812000159, DOI: https://dx.doi.org/10.21275/SR22812000159