This book is a new contribution aiming to give some last research findings in the field of optimization and computing. This work is in the same field target than our two previous books published: “Recent Developments in Metaheuristics” and “Metaheuristics for Production Systems”, books in Springer Series in Operations Research/Computer Science Interfaces. The challenge with this work is to gather the main contribution in three fields, optimization technique for production decision, general development for optimization and computing method and wider spread applications. The number of researches dealing with decision maker tool and optimization method grows very quickly these last years and in a large number of fields. We may be able to read nice and worthy works from research developed in chemical, mechanical, computing, automotive and many other fields.

This book explores how developing solutions with heuristic tools offers two major advantages: shortened development time and more robust systems. It begins with an overview of modern heuristic techniques and goes on to cover specific applications of heuristic approaches to power system problems, such as security assessment, optimal power flow, power system scheduling and operational planning, power generation expansion planning, reactive power planning, transmission and distribution planning, network reconfiguration, power system control, and hybrid systems of heuristic methods.

This book offers a thorough overview of the most popular and researched meta-heuristic optimization techniques and nature-inspired algorithms. Their wide applicability makes them a hot research topic and an effi cient tool for the solution of complex optimization problems in various fi elds of sciences, engineering, and in numerous industries.

Theoretical results suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g. in vision, language, and other AI-level tasks), one may need deep architectures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. Searching the parameter space of deep architectures is a difficult task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the state-of-the-art in certain areas. This paper discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.

This volume constitutes selected papers presented during the 8th International Conference on Metaheuristics and Nature Inspired Computing, META 2021, held in Marrakech, Morocco, in October 201. Due to the COVID-19 pandemic the conference was partiqally held online. The 16 papers were thoroughly reviewed and selected from the 53 submissions. They are organized in the topical sections on ​combinatorial optimization; continuous optimization; optimization and machine learning; applications.

Combinatorial optimization is the process of finding the best, or optimal, so lution for problems with a discrete set of feasible solutions. Applications arise in numerous settings involving operations management and logistics, such as routing, scheduling, packing, inventory and production management, lo cation, logic, and assignment of resources. The economic impact of combi natorial optimization is profound, affecting sectors as diverse as transporta tion (airlines, trucking, rail, and shipping), forestry, manufacturing, logistics, aerospace, energy (electrical power, petroleum, and natural gas), telecommu nications, biotechnology, financial services, and agriculture. While much progress has been made in finding exact (provably optimal) so lutions to some combinatorial optimization problems, using techniques such as dynamic programming, cutting planes, and branch and cut methods, many hard combinatorial problems are still not solved exactly and require good heuristic methods. Moreover, reaching "optimal solutions" is in many cases meaningless, as in practice we are often dealing with models that are rough simplifications of reality. The aim of heuristic methods for combinatorial op timization is to quickly produce good-quality solutions, without necessarily providing any guarantee of solution quality. Metaheuristics are high level procedures that coordinate simple heuristics, such as local search, to find solu tions that are of better quality than those found by the simple heuristics alone: Modem metaheuristics include simulated annealing, genetic algorithms, tabu search, GRASP, scatter search, ant colony optimization, variable neighborhood search, and their hybrids.

This book is a collection of the most recent approaches that combine metaheuristics and machine learning. Some of the methods considered in this book are evolutionary, swarm, machine learning, and deep learning. The chapters were classified based on the content; then, the sections are thematic. Different applications and implementations are included; in this sense, the book provides theory and practical content with novel machine learning and metaheuristic algorithms. The chapters were compiled using a scientific perspective. Accordingly, the book is primarily intended for undergraduate and postgraduate students of Science, Engineering, and Computational Mathematics and is useful in courses on Artificial Intelligence, Advanced Machine Learning, among others. Likewise, the book is useful for research from the evolutionary computation, artificial intelligence, and image processing communities.