Cantitate/Preț
Produs
Total produse
Vezi coșul
Advanced Machine Learning with Evolutionary and Metaheuristic Techniques de Jayaraman Valadi

Advanced Machine Learning with Evolutionary and Metaheuristic Techniques: Computational Intelligence Methods and Applications

Editat de Jayaraman Valadi, Krishna Pratap Singh, Muneendra Ojha, Patrick Siarry
en Limba Engleză Paperback – 23 apr 2025

Bazându-ne pe cele mai recente date din seria Computational Intelligence Methods and Applications a editurii Springer, observăm o lucrare colectivă care redefinește intersecția dintre algoritmii de optimizare și procesele de învățare automată. Ediția 2024, Advanced Machine Learning with Evolutionary and Metaheuristic Techniques, se concentrează pe implementarea practică a algoritmilor evolutivi pentru a extinde capacitățile modelelor data-driven. Descoperim aici o abordare riguroasă a modului în care metaheuristica poate fi utilizată pentru a construi cadre de deep learning mai eficiente și pentru a optimiza hiperparametrii în contextul transfer learning-ului.

Structura volumului este progresivă, începând cu bazele teoretice ale sinergiei dintre optimizare și inteligența artificială (capitolele 1-3) și continuând cu aplicații tehnice complexe. Suntem de părere că includerea unor teme precum inteligența artificială explicabilă (XAI) și integrarea Particle Swarm Optimization cu Reinforcement Learning oferă cititorului instrumente avansate pentru probleme de optimizare dinamică. Lucrarea este comparabilă cu Handbook of Evolutionary Machine Learning de Wolfgang Banzhaf în ceea ce privește rigoarea, dar este actualizată pentru noile provocări din rețelele IoT și mecanica materialelor, domenii unde optimizarea eficientă a resurselor este critică.

Această publicație extinde direcțiile explorate anterior de coordonatorii volumului în Applications of Metaheuristics in Process Engineering, trecând de la simplitatea algoritmilor paralelizabili la sisteme inteligente de detecție a anomaliilor. Prin cele 372 de pagini, editorii Jayaraman Valadi și Patrick Siarry reușesc să facă tranziția de la teoria abstractă la soluții inginerești concrete, precum sistemul de detecție a atacurilor RPL pentru rețelele IoT, demonstrând utilitatea metaheuristicii în securitatea cibernetică contemporană.

Citește tot Restrânge

Din seria Computational Intelligence Methods and Applications

Preț: 138764 lei

Preț vechi: 173455 lei
-20%

Puncte Express: 2081
Paperback 138764 lei
Hardback 118425 lei

Carte tipărită la comandă

Livrare economică 22-28 mai

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă

Specificații

ISBN-13: 9789819997206
ISBN-10: 9819997208
Pagini: 372
Dimensiuni: 155 x 235 x 21 mm
Greutate: 0.56 kg
Editura: Springer
Colecția Computational Intelligence Methods and Applications
Seria Computational Intelligence Methods and Applications

De ce să citești această carte

Această carte este esențială pentru cercetătorii și inginerii care doresc să depășească limitările algoritmilor standard de învățare automată. Cititorul câștigă acces la strategii avansate de optimizare a hiperparametrilor și tehnici de fuziune între optimizarea prin roiuri și învățarea prin întărire. Este un ghid practic pentru implementarea soluțiilor de AI în domenii critice precum IoT și ingineria proceselor, oferind un avantaj competitiv în dezvoltarea modelelor de deep learning.

Despre autor

Volumul este coordonat de o echipă de experți recunoscuți, printre care se numără Jayaraman Valadi și Patrick Siarry. Patrick Siarry este un profesor și cercetător cu o vastă experiență în domeniul metaheuristicii aplicate, fiind cunoscut pentru lucrările sale care simplifică aplicabilitatea algoritmilor de optimizare combinatorie în inginerie. Contribuția sa la această ediție Springer reflectă o carieră dedicată eficientizării proceselor industriale prin inteligență computațională, axându-se pe transformarea modelelor matematice complexe în instrumente de lucru accesibile pentru comunitatea academică și tehnică.

Cuprins

Chapter 1. From Evolution to Intelligence: Exploring the Synergy of Optimization and Machine Learning.- Chapter 2. Metaheuristic and Evolutionary Algorithms in Ex-plainable Artificial Intelligence.- Chapter 3. Evolutionary Dynamic Optimization and Machine Learning.- Chapter 4. Evolutionary Techniques in making Efficient Deep-Learning Framework: A Review.- Chapter 5. Integrating Particle Swarm Optimization with Reinforcement Learning: A Promising Approach to Optimization.- Chapter 6. Synergies between Natural Language Processing and Swarm Intelligence Optimization: A Comprehensive Overview.- Chapter 7. Heuristics-based Hyperparameter Tuning for Transfer Learning Algorithms.- Chapter 8. Machine Learning Applications of Evolutionary and Metaheuristic Algorithms.- Chapter 9. Machine Learning Assisted Metaheuristic Based Optimization of Mixed Suspension Mixed Product Removal Process.- Chapter 10. Machine Learning based Intelligent RPL Attack Detection System for IoT Networks.- Chapter 11. Shallow and Deep Evolutionary Neural Networks applications in Solid Mechanics.- Chapter 12. Polymer and nanocomposite Informatics: Recent Applications of Artificial Intelligence and Data Repositories.- Chapter 13. Synergistic combination of machine learning and evolutionary and heuristic algorithms for handling imbalance in biological and biomedical datasets.


Notă biografică

Dr. Jayaraman Valadi  is a Distinguished Professor of Computer Science at FLAME University, Pune, India. He earned his Doctorate degree in Chemistry from Pune University. His research encompasses diverse areas, focusing on modeling and simulations in chemical and biochemical engineering, as well as process modeling, control, and optimization. Over the past decade, he has dedicated his efforts to exploring applications of Machine Learning and Artificial intelligence across various domains. He has dozens of publications in various reputed international journals. Beginning his journey in 1976, Dr. Valadi was associated with the Council of Industrial and Scientific Research (CSIR) in India, where he worked for 33 years and retired as a Deputy Director in 2009. After that, he was a CSIR Emeritus Scientist at the Center for Development of Advanced Computing, Pune till January 2013 & thereafter as a visiting faculty at Shiv Nadar University, Greater Noida, India until May 2023.
 
Dr. Krishna Pratap Singh is an Associate Professor in the Department of Information Technology at the Indian Institute of Information Technology Allahabad (IIITA), India, where he also heads the Machine Learning and Optimization (MLO) Lab. Dr. Singh earned his Ph.D. in Optimization (2009) from IIT Roorkee, and has over 15 years of research and academic experience. He is a member of the Sakura Science Club, Japan, Senior member IEEE and ACM Member. Currently, his research group is working on Transfer Learning for low resources data and towards developing a model in a Federated learning setting.
 
Dr. Muneendra Ojha is an Assistant Professor in the Department of Information Technology at the Indian Institute of Information Technology Allahabad (IIITA), India, and leading the Artificial Intelligence and Multiagent Systems (AIMS) lab. Dr. Ojha earned his Ph.D. from IIITA and MS from the University of Missouri-Columbia, USA.Dr. Ojha has more than 19 years of academic and industry experience. His research interests include multi-objective optimization, evolutionary algorithms, semantic web, natural language processing, deep reinforcement learning, and multi-agent systems.
 
Dr. Patrick Siarry received the PhD degree from the University Paris 6, in 1986 and the Doctorate of Sciences(Habilitation) from the University of Paris 11, in 1994. He was first involved in the development of analog and digital models of nuclear power plants at  Electricité de France (EDF. Since 1995 he is a full Professor of automatics and informatics. His main research interests are the adaptation of new stochastic global optimization heuristics to various situations (multi objective mixed discrete-continuous variables, continuous variables, dynamic,etc.) and their application to various engineering fields. He is also interested in the fitting of process models to experimental data and thelearning of fuzzy rule bases and neural networks. P.Siarry is a senior member  IEEE,  an appointed member of the Technical Committee on Soft Computing of the IEEE systems, Man and Cybernetics (SMC) Society and an appointed member of the Technical Committee on Optimal Control (TC 2.4) of IFAC.

Textul de pe ultima copertă

This book delves into practical implementation of evolutionary and metaheuristic algorithms to advance the capacity of machine learning. The readers can gain insight into the capabilities of data-driven evolutionary optimization in materials mechanics, and optimize your learning algorithms for maximum efficiency. Or unlock the strategies behind hyperparameter optimization to enhance your transfer learning algorithms, yielding remarkable outcomes. Or embark on an illuminating journey through evolutionary techniques designed for constructing deep-learning frameworks. The book also introduces an intelligent RPL attack detection system tailored for IoT networks. Explore a promising avenue of optimization by fusing Particle Swarm Optimization with Reinforcement Learning.
 
It uncovers the indispensable role of metaheuristics in supervised machine learning algorithms. Ultimately, this book bridges the realms of evolutionary dynamic optimization and machine learning, paving the way for pioneering innovations in the field.

Caracteristici

A comprehensive exploration of evolutionary and metaheuristic algorithms applied to various aspects of machine learning Showcases how evolutionary and metaheuristic algorithms are revolutionizing industries like biomed and healthcare Integrates different domains of AI, including evolutionary algorithms, metaheuristics, reinforcement learning, etc.