Murat Kuzlu, associate professor in the Department of Engineering Technology, recently co-authored a book titled, “
Tailored for artificial intelligence (AI) developers, researchers and end-users, the book offers theoretical insights and practical guidance for building, deploying and testing trustworthy AI models.
Kuzlu and co-author, Ferhat Ozgur Catak, an associate professor at the University of Stavanger, Norway, discuss the use of artificial intelligence across various fields, in particular, academia and industry, and the challenges related to the trustworthiness of AI systems in terms of reliability, fairness, transparency, privacy and security.
“In this book, we aim to bridge the gap between theoretical concepts of trustworthy AI, along with sharing their practical applications using Python and open-source libraries,” Kuzlu explained. The open-source code is published on
The methodology is accessible to anyone with an understanding of fundamental AI concepts and programming skills, particularly in Python. Kuzlu recommends familiarity with open-source libraries relevant to AI development as well.
Kuzlu is optimistic about its future of trustworthy AI. “I believe we can collectively form a future where AI technologies are not only powerful and efficient but also ethical, fair, and responsible, ultimately benefiting society,” he said.
Kuzlu joined in 2018. His expertise lies in cyber-physical systems, smart systems, artificial intelligence, trustworthy AI, and next-generation networks.