Artificial Intelligence (Machine Learning & Deep Learning) Basics for Pharmaceutical Sciences Students & Professionals

by Amit Gangwal, Ankit Gangwal

The book has been designed to cover all the essential topics and examples related to artificial intelligence, machine learning and deep learning in three chapters, respectively. This book is designed to cater to the basic needs of students and professionals of pharmaceutical sciences, nursing, medicine, and other life sciences streams who want to learn the basics of these emerging technologies without any background in data science or, coding, etc. More and more pharma companies are using artificial intelligence and its subsets for increasing productivity in terms of drug discovery (molecular property prediction, de novo drug design, novel receptor finding, repurposing, ADMET profiles, etc.), manufacturing, clinical trials (subject selection, data recording and analyzing, minimizing dropping out of subjects, etc.), synthesis, logistics, sales, marketing, and others. In this book, different types of tasks (machine learning and deep learning can handle) have been described in a very easy-to-understand fashion; besides types of machine learning (like supervised, unsupervised and reinforcement learning), machine learning algorithms etc. Basics, like models, features, vectors, weights, biases, training, testing, data processing, etc., are all covered in detail. Various types of artificial neural networks like convolutional neural networks, recurrent neural networks, autoencoders (and its types like variational autoencoder, adversarial autoencoder) and much talked about generative artificial intelligence models like generative adversarial networks and others have also been covered in a significant manner. Large language models/transformers have also been discussed (the much talked about techniques behind ChatGPT). All topics are explained in very simple language with precise aim. Professionals from the medical, pharmacy, pharma industries, nursing and dental, and medical imaging arenas will find this book very useful if they want
vii
to explore the basics and applications of AI. Students of all levels will discover the book very beneficial as few topics have been touched on, few have been shallow in complexity, and the rest are covered in detail. Depending on the section or your current learning in the book, topics are first introduced, and in latter sections, they have been elaborated in length. Extensive focus has been made on comparative analysis in tabular sheets for easy understanding and analysis.
Readers should not get confused while reading similar things repeatedly in chapters. For instance, the challenges artificial intelligence is facing will appear identical in machine learning and deep learning as well. This is because machine learning and deep learning are parts of artificial intelligence only. This overlapping is inevitable owing to the unintentional frequent interchangeability of these three terms in current times. This intentional repetition in the book will further prevent readers from going back to earlier read pages. We believe that research (and, therefore, progress in these fields) is going on at an unprecedented pace; thus, the challenges and limitations mentioned in this book will vanish over the years. In this context, readers must update/enrich their knowledge by exposing themselves to the latest literature. At the end of each Chapter, sufficient questions have been provided. These questions will assess reader comprehension, reinforcing learned concepts and promoting active engagement. Designed for self-assessment, these questions encourage critical thinking and application of knowledge, preparing readers for exams and facilitating group discussions. Instructors may use them to guide assessments and class activities. Overall, these questions enhance the learning experience, ensuring a thorough understanding of the material and fostering a deeper connection between the reader and the content.

Kindle Edition

Published December 13, 2023