Prajit Kulkarni has nearly 20 years of experience working in the digital signal processing domain. His experience spans digital filter design, image processing algorithms for camera systems, video compression standards and computer vision. He has ventured into the vast wilderness of machine learning over the past few years. He has worked on optimizing algorithms for hardware implementation at companies such as Aptina, Qualcomm and Amazon Lab126. His motivation to write this book was the unavailability of a single comprehensive source that could effectively introduce Transformers to a novice without relying on a large number of external references or fragments of code to explain key concepts.