November 17, 2023
Arslan Munir authors 'Accelerators for Convolutional Neural Networks'
Arslan Munir, Daniel and Judi Burk — Carl and Mary Ice Keystone Research Scholar and associate professor of computer science at Kansas State University, has authored a new book, "Accelerators for Convolutional Neural Networks," which is published by Wiley-IEEE press.
Munir worked alongside Joonho Kong, an associate professor of electronics engineering at Kyungpook National University, Republic of Korea, and Mahmood Azhar Qureshi, an alumnus and currently a senior IP design engineer at Intel Corporation, in authoring this book.
The book provides basic deep learning knowledge and instructive content to build up convolutional neural network, or CNN, accelerators for the Internet of things, or IoT, and edge computing practitioners, elucidating compressive coding for CNNs. This presents a two-step lossless input feature maps compression method, discussing arithmetic coding-based lossless weights compression method and the design of an associated decoding method, describing contemporary sparse CNNs that consider sparsity in both weights and activation maps, and discussing hardware/software co-design and co-scheduling techniques that can lead to better optimization and utilization of the available hardware resources for CNN acceleration.
For researchers in artificial intelligence, computer vision, computer architecture and embedded systems, along with graduate and senior undergraduate students in related programs of study, this book is a valuable resource to understanding the many facets of the subject and relevant applications.