August 23, 2023
Hitzler publishes book on neurosymbolic artificial intelligence
Pascal Hitzler, Lloyd T. Smith creativity in engineering chair and professor of computer science at Kansas State University, led a team of K-State computer scientists in publishing an edited book, "Compendium of Neurosymbolic Artificial Intelligence."
Hitzler worked alongside Md Kamruzzaman Sarker, an alumnus and current assistant professor in the computing sciences department at the University of Hartford, and Aaron Eberhart, doctoral student in computer science at K-State.
The book presents 30 invited chapters that explore various approaches to defining and developing successful systems that combine two major methods in artificial intelligence: deep learning and symbolic knowledge representation. Each method has clear advantages and disadvantages, while combinations aim at finding some useful middle ground between the rigid transparency of symbolic systems and the more flexible yet highly opaque neural methods.
The papers are organized by theme, with the first four being overviews or surveys of the field. These are followed by papers covering neurosymbolic reasoning, neurosymbolic architectures, various aspects of deep learning and finally, two chapters on natural language processing. Each paper was reviewed internally before publication.
The book is intended to follow and extend the work of Hitzler's previous book, published by IOS Press in 2021, "Neuro-Symbolic Artificial Intelligence: The State of the Art," which laid out the breadth of the field at that time.
Neurosymbolic AI is a young field that is still being actively defined and explored, and this book will be of interest to those working in AI research and development.
The book is available as an eBook or print version from IOS Press.