A Unifying Framework for Formal Theories of Novelty (eBook)

Discussions, Guidelines, and Examples for Artificial Intelligence

Terrance Boult, Walter Scheirer (Herausgeber)

eBook Download: PDF

2023
110 Seiten
Springer Nature Switzerland (Verlag)
978-3-031-33054-4 (ISBN)

Infos

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.  

                

Produkt-Details

• Erscheint lt. Verlag: 1.8.2023
• Reihe/Serie: Synthesis Lectures on Computer Vision
• Reihe/Serie: Synthesis Lectures on Computer Vision
• Zusatzinfo: XV, 110 p. 35 illus., 33 illus. in color.
• Sprache: englisch
• Original-Titel: Impossibility Results for Distributed Computing
• Themenwelt: Mathematik / Informatik ► Informatik ► Grafik / Design
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Mathematik / Informatik ► Mathematik ► Statistik
• Themenwelt: Technik ► Elektrotechnik / Energietechnik
• Schlagworte: Anomaly Detection • Computer Science • computer vision • Control-based Systems • machine learning • Multi-Agent Game Domain • multi-player games • Novelty detection • Novelty Theories • Open-set Recognition • Open-world Learning • Planning-based Systems • Symbolic-reasoning
• ISBN-10: 3-031-33054-4 / 3031330544
• ISBN-13: 978-3-031-33054-4 / 9783031330544