This book presents the first unified formalization for defining novelty across the span of machine learning, symbolic-reasoning, and control and planning-based systems. Dealing with novelty, things not previously seen by a system, is a critical issue for building vision-systems and general intelligent systems. The book presents examples of using this framework to define and evaluate in multiple domains including image recognition image-based open world learning, hand-writing and author analysis, CartPole Control, Image Captioning, and Monopoly. Chapters are written by well-known contributors to this new and emerging field. In addition, examples are provided from multiple areas, such as machine-learning based control problems, symbolic reasoning, and multi-player games.

Addresses novelty to enhance building both vision-systems and planning-based systems Establishes formal definitions of novelty subtypes that will help produce a consistent lexicon for researchers Includes examples of applications, including image captioning, multi-agent game domain, and handwriting recognition

Autorentext
Terrance E. Boult, Ph.D., is a Distinguished Professor and El Pomar Endowed Professor of Innovation and Security in the Department of Computer Science at the University of Colorado at Colorado Springs. He is also an IEEE Fellow and an internationally acknowledged researcher in machine learning, computer vision, biometrics, and cybersecurity with 15 patents issued and 400+ articles. Dr. Boult received the B.S. degree in Applied Mathematics, the M.S. degree in Computer Science, and the Ph.D. degree in Computer Science from Columbia University. He has won multiple teaching awards, research/innovation awards, best paper awards, best reviewer awards, and IEEE service awards.

Walter Scheirer, Ph.D., is Dennis O. Doughty Collegiate Associate Professor in the Department of Computer Science and Engineering at the University of Notre Dame. Previously, he was a postdoctoral fellow at Harvard University with affiliations in the Schoolof Engineering and Applied Sciences, Department of Molecular and Cellular Biology, and Center for Brain Science. Dr. Scheirer received his Ph.D. from the University of Colorado and his M.S. and B.A. degrees from Lehigh University. He has extensive experience in the areas of computer vision, machine learning, and image processing. His current research is focused on media forensics and studying disinformation circulating on social media.

Inhalt
A Unifying Framework for Novelty.- Example Application of Framework: CartPole Domain.- Image Classification.- Novelty in Handwriting Recognition.- Visual Media Caption Domain.- Monopoly Multi-Agent Game Domain.- Related Work.- Prior Perspectives on Novelty and Conclusions. <p