Computational Intelligence Techniques Machine Learning Hybridization and Optimization for Intelligent Applications

This book discusses state-of-the-art reviews of the existing machine-learning techniques and algorithms including hybridizations and optimizations. It is aimed at graduate students and researchers in machine learning, artificial intelligence, and electrical engineering. This book discusses state-of-the-art reviews of the existing machine learning techniques and algorithms including hybridizations and optimizations. It covers applications of machine learning via artificial intelligence (AI) prediction tools, discovery of drugs, neuroscience, diagnosis in multiple imaging modalities, pattern recognition approaches to functional magnetic resonance imaging, image and speech recognition, automatic language translation, medical diagnostic, stock market prediction, traffic prediction, and product automation. Features: Focuses on hybridization and optimization of machine learning techniques Reviews supervised, unsupervised, and reinforcement learning using case study-based applications Covers the latest machine learning applications in as diverse domains as the Internet of Things, data science, cloud computing, and distributed and parallel computing Explains computing models using real-world examples and dataset-based experiments Includes case study-based explanations and usage for machine learning technologies and applications This book is aimed at graduate students and researchers in machine learning, artificial intelligence, and electrical engineering.