Preface

Machine Learning proved its usefulness in many applications in the domain of Image Processing and Computer Vision, Medical Imaging, Satellite imaging, Remote Sensing, Surveillance, etc ., over the past decade. At the same time, Machine Learning methods themselves have evolved, particularly deep learning methods that have demonstrated significant performance over traditional machine learning algorithms.

Today’s Deep Learning has become researchers’ first choice in contrast to traditional machine learning due to its apex performance in many applications in the domain of speech, image, and text processing. Deep learning algorithms provide efficient solutions to problems ranging from vision and speech to text processing. The research on deep learning is getting enriched day by day as we witness new learning models.

This book contains two major parts. Part one includes the fundamentals of Deep Learning, theory, and architecture of Deep Learning. Moreover, this part provides a detailed description of the theory, frameworks, and non-conventional approaches to deep learning. It covers foundational mathematics that is essential in understanding the framework. Moreover, it covers various kinds of models found in practice.

Chapter 1 contains the basic operating understanding, history, evolution, and challenges associated with deep learning. We will also cover some basic concepts of mathematics and the hardware requirements for deep learning implementation, and some of its popular software frameworks. We will start with neural networks, which focus on the basics of neural networks, including input/output layers, hidden layers, and how networks learn through forward and backpropagation. We will also cover the standard multilayer perceptron networks and their building blocks. Moreover, we will include a review of deep learning concepts in general and deep learning in particular to build a basic understanding of this book. Chapters 2–7 are based on applying artificial intelligence to medical images with various deep learning approaches. It also covers the application of Deep Learning in lung cancer detection, medical imaging, and COVID-19 analysis.

The second part, chapters 8–10, is dedicated to sentiment analysis using deep learning and machine learning techniques. This book section covers the experimentation and application of deep learning techniques and architectures in real-world applications. It details the salient approaches, issues, and challenges in building ethically aligned machines. An approach inspired by traditional Eastern thought and wisdom is also presented.

The third part, Chapters 11–15, is miscellaneous and covers the different artificial intelligence approaches used to explain the machine learning models that enhance transparency between the user and the model. A review and detailed description of the use of knowledge graphs in generating explanations for black-box recommender systems and elaborative education ecosystems for sustainable quality education is provided. Reinforcement learning is a semi-supervised learning technique for portfolio management.