Comprehensive guide on learning automata, introducing two variants to accelerate convergence and computational update speed
Learning Automata and Their Applications to Intelligent Systems provides a comprehensive guide on learning automata from the perspective of principles, algorithms, improvement directions, and applications. The text introduces two variants to accelerate the convergence speed and computational update speed, respectively; these two examples demonstrate how to design new learning automata for a specific field from the aspect of algorithm design to give full play to the advantage of learning automata.
As noisy optimization problems exist widely in various intelligent systems, this book elaborates on how to employ learning automata to solve noisy optimization problems from the perspective of algorithm design and application.
The existing and most representative applications of learning automata include classification, clustering, game, knapsack, network, optimization, ranking, and scheduling. They are well-discussed. Future research directions to promote an intelligent system are suggested.
Written by two highly qualified academics with significant experience in the field, Learning Automata and Their Applications to Intelligent Systems covers such topics as:
- Mathematical analysis of the behavior of learning automata, along with suitable learning algorithms
- Two application-oriented learning automata: one to discover and track spatiotemporal event patterns, and the other to solve stochastic searching on a line
- Demonstrations of two pioneering variants of Optimal Computing Budge Allocation (OCBA) methods and how to combine learning automata with ordinal optimization
- How to achieve significantly faster convergence and higher accuracy than classical pursuit schemes via lower computational complexity of updating the state probability
A timely text in a rapidly developing field, Learning Automata and Their Applications to Intelligent Systems is an essential resource for researchers in machine learning, engineering, operation, and management. The book is also highly suitable for graduate level courses on machine learning, soft computing, reinforcement learning and stochastic optimization.
JunQi Zhang, PhD, is a Full Professor with Tongji University in Shanghai. He has published 10+ papers in IEEE Transactions and 30+ papers in conferences. His current research interests include learning automata, swarm intelligence, swarm robots, multi-agent systems, reinforcement learning, and big data.
MengChu Zhou, PhD, is a Distinguished Professor at New Jersey Institute of Technology. He has over 1100 publications including 14 books, 750+ journal papers (600+ in IEEE transactions), 31 patents, and 32 book-chapters. He is Fellow of IEEE, IFAC, AAAS, CAA and NAI.
