Introduction -- Metadata Extraction and Data Preprocessing -- Data Exploration -- Practice Exercises -- Supervised Learning -- Unsupervised Learning -- Reinforcement Learning -- Model Evaluation and Optimization -- ML in Computer vision - autonomous driving and object recognition -- ML in Health-care - ECG and EEG analysis -- ML in Embedded Systems - resource management -- ML for Security (Malware) -- ML in Big-data Analytics -- ML in Recommender Systems -- ML for Ontology Acquisition from Text and Image Data -- Adversarial Learning -- Graph Adversarial Neural Networks -- Graph Convolutional Networks -- Hardware for Machine Learning -- Software Frameworks.

This textbook introduces readers to the theoretical aspects of machine learning (ML) algorithms, starting from simple neuron basics, through complex neural networks, including generative adversarial neural networks and graph convolution networks. Most importantly, this book helps readers to understand the concepts of ML algorithms and enables them to develop the skills necessary to choose an apt ML algorithm for a problem they wish to solve. In addition, this book includes numerous case studies, ranging from simple time-series forecasting to object recognition and recommender systems using massive databases. Lastly, this book also provides practical implementation examples and assignments for the readers to practice and improve their programming capabilities for the ML applications. Describes traditional as well as advanced machine learning algorithms; Enables students to learn which algorithm is most appropriate for the data being handled; Includes numerous, practical case-studies; implementation codes in Python available for readers; Uses examples and exercises to reinforce concepts introduced and develop skills.