About the book
The book will cover all relevant concepts in machine learning and deep learning including supervised learning, semi-supervised learning, and unsupervised learning approaches. It will cover regression, classification, and clustering approaches to machine learning, predictive model building, model optimization using hyperparameter tuning etc. It will then delve into deep learning model architectures, their design, and optimization issues including the design of multi-layer perceptrons, deep neural networks, autoencoders, restricted Boltzmann machines, convolutional neural networks, long-and-short-term memory (LSTM) networks, recurrent neural networks.
Finally, the book will address core issues related to artificial intelligence particularly focusing on reinforcement learning-based systems. The contributions in the book can be either of three forms - (1) concepts of machine learning explained in a tutorial format for understanding of some concepts, (2) research contributions based on designing new algorithms and applications presenting some novel results, and (3) innovative applications of well-known theories and concepts. The chapters in the book will largely be based on the following topics but not necessarily limited to them: planning, design testing, and deployment of machine learning projects, classification models, regression models, support vector machines, decision trees, ensemble models, multilayer perceptions, training, validation, and testing of models, dimensionality reduction - singular value decomposition, principal component analysis, hyperparameter tuning, model optimization, deep neural networks, autoencoders, restricted Boltzmann machines, convolutional neural networks, recurrent neural networks, reinforcement learning, temporal difference learning etc.