Advances in Neural Network Optimization

Metaheuristic Algorithms and Applications
1. Auflage 2027
ISBN: 978-1-041-17228-4
Verlag: CRC Press

Buch, Englisch, 448 Seiten, Format (B × H): 210 mm x 280 mm

Reihe: Advances in Metaheuristics

Advances in Neural Network Optimization: Metaheuristic Algorithms and Applications introduces readers to one of the most important challenges in modern artificial intelligence: how to make neural networks faster, smarter, more accurate, and more efficient. Written for a wide academic and professional readership, the book explains how nature-inspired optimization can improve intelligent systems across science, engineering, healthcare, energy, and industry.

The volume brings together advanced studies on neural network optimization, metaheuristic algorithms, and their practical applications in emerging intelligent systems. It covers foundational and contemporary approaches such as Grey Lag Goose Optimization, Grey Goose Optimization, whale optimization, swarm intelligence, evolutionary computation, quantum-inspired optimization, reinforcement learning-based neural architecture search, gradient-free learning, and hybrid hyperparameter optimization. The chapters examine how these techniques can be used to improve neural network training, architecture design, pruning, quantization, regularization, automated machine learning, and physically constrained neural networks. The book also extends these methods into applied domains including smart energy, manufacturing, agriculture, cloud-based organizational transformation, communication networks, medical imaging, lung cancer detection, dysarthric speech classification, machine translation, electric motor design, federated learning, resource utilization prediction, and sustainable computation. By combining theory, algorithmic development, surveys, comparative evaluations, and application-focused research, the book provides a broad and integrated view of optimization in next-generation AI systems. The originality of this book lies in its strong connection between metaheuristic theory and real-world neural network applications. It demonstrates how alternative optimization methods can overcome the limits of conventional gradient-based approaches, especially in complex, nonlinear, resource-constrained, and high-dimensional problems. The book will be particularly useful for researchers, postgraduate students, AI developers, data scientists, engineers, and professionals working on intelligent optimization, sustainable AI, and advanced machine learning systems.

Zielgruppe

Academic and Postgraduate

Autoren/Hrsg.

Dutta, Pushan Kumar

Bhattacharya, Pronaya

Kumar Singh, Sushil

Mamodiya, Udit

William, P

Fachgebiete

• Mathematik | Informatik EDV | Informatik Daten / Datenbanken
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Neuronale Netzwerke
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Mathematik | Informatik Mathematik Numerik und Wissenschaftliches Rechnen Optimierung

Inhaltsverzeichnis

Editor Biographies. Chapter 1. Foundations of Metaheuristic Optimization for Sustainable Intelligent Systems. Chapter 2. Greylag Goose Optimization (GGO): Theory & Implementation. Chapter 3. Metaheuristics in Neural Architecture Search and Hyperparameter Tuning. Chapter 4. Emerging Nature-Inspired and Alternative Optimization Algorithms. Chapter 5. Optimizing Smart Energy, Manufacturing, and Agriculture with Metaheuristics. Chapter 6. Systematic Hyper Parameter in Neural Network Optimization. Chapter 7. Greylag Goose Optimization in Medical Applications: A Comprehensive Review of Advances and Challenges. Chapter 8. Metaheuristic Algorithms for Neural Network Optimization: Recent Advances and Emerging Applications. Chapter 9. Swarm Intelligence and Bio-Inspired Algorithms: Nature-Driven Optimization for Intelligent Systems. Chapter 10. Fundamentals and Advances in Neural Network Optimization. Chapter 11. Analyzing Online Service Index as an Indicator of Cloud-Based Organizational Transformation Through EGDI Analysis. Chapter 12. A Neural Network-Driven Approach for Optimizing Communication in Perfect Difference Interconnection Networks. Chapter 13. Gradient-Free and Alternative Optimization Techniques. Chapter 14. A Survey on Nature-Inspired Optimization Algorithms. Chapter 15. Metaheuristics in Context from Theory to Sustainable Intelligent Systems. Chapter 16. Industrial Applications of AI in Electric Motor Design Using Whale Optimization Algorithm. Chapter 17. A Systematic Review of PET/CT-Based Lung Cancer Detection Using Machine Learning Methods. Chapter 18. Evolutionary Strategies for Sustainable Neural Networks. Chapter 19. Hybrid GGO-Quantum Computing Approaches for Large-Scale Optimization Problems. Chapter 20. Large-Scale Comparative Evaluation of Speech Features for Dysarthric Speech Classification Using the TORGO Database. Chapter 21. Neural Machine Translation for English-Hindi Using LSTM and Greylag Goose Optimization. Chapter 22. Swarm Intelligence for Edge-AI and Sustainable Computation: A Bioinspired Neuro-Optimization Perspective. Chapter 23. Advances in Deep Learning and AI-Based CAD Systems for Lung Cancer Detection Using CT Imaging. Chapter 24. Foundational Optimization Methods in Deep Learning: A Unified Geometric Perspective. Chapter 25. An Enhanced Hybrid Metaheuristic Algorithm (EHMA) for Optimizing Deep Neural Network Architectures. Chapter 26. Metaheuristic Optimization of Physically Constrained Neural Networks for Engineering Systems. Chapter 27. Intelligent Hyper-Parameter Optimization: A Comprehensive Framework for Automated Machine Learning Systems. Chapter 28. The Hyperparameter Optimisation Revolution: Techniques, Benchmarks, and Pathways for Scalable ML in Manufacturing. Chapter 29. Automated Machine Learning: Advancing Neural Network Optimization through Hyperparameter Optimization and Architecture Search. Chapter 30. Reinforcement Learning-Based Neural Architecture Search for Automated Model Design. Chapter 31. Energy-Efficient Distributed and Federated Learning for Smart Agriculture. Chapter 32. Beyond Gradient Descent: Advances in Metaheuristic Optimization Techniques for Deep Neural Networks. Chapter 33. Deep Learning for Resource Utilization Prediction in Cloud Data Centers. Chapter 34. Integrating GGO into Regularization Techniques & Pruning and Quantization Optimization via GGO. Chapter 35. Behavioral Parameter Optimization: Meta Optimization Across Algorithms. Chapter 36. Application of Metaheuristic Neural Networks in Life Sciences. Chapter 37. Adaptive Metaheuristics and Evolutionary Computing for Next-Generation Optimization Systems. Chapter 38. Comparative Analysis of Swarm Intelligence-Based Cooperative Techniques for Target Search.

Über Autor(innen)

Dr. Pushan Kumar Dutta, Erasmus Mundus Post-Doctoral Fellow, is Associate Professor at Amity University Kolkata, book series editor, researcher, mentor, Associate Editor of JBHI, and Editor-in-Chief of Quanta Research, TULTECH. With over 60 Scopus-indexed editorials, he actively

Dr. Pronaya Bhattacharya is a globally recognized network and security researcher, ranked among the World’s Top 1% Scientists by Stanford in 2023, 2024, and 2025. He serves as Head of CSE at Amity School of Engineering and Technology, Amity University Kolkata, advancing impactful computing research and academic leadership.

Dr. Sushil Kumar Singh is an Associate Professor in Computer Engineering at Marwadi University, Rajkot. A Postdoctoral researcher from London Metropolitan University and Ph.D. from SeoulTech, he works on blockchain, AI, IoT, cybersecurity, smart cities, and secure emerging technologies.

Dr. Udit Mamodiya is Associate Professor and Associate Dean (Research) at Poornima University, Jaipur. His research spans fuzzy logic, neural networks, electronics, AI, and emerging technologies. He actively contributes to academic research leadership, interdisciplinary collaboration, conference organization, and innovation-driven higher education.

Dr. P. William is Director–Research & Development at Sanjivani University, India. A postdoctoral researcher and globally recognized academic, he works across AI, NLP, cybersecurity, deep learning, cloud computing, and innovation, with extensive contributions to Scopus-indexed research, edited books, patents, and scholarly leadership.