Efficient out-of-distribution detection using latent space of β-VAE for cyber-physical systems

• Main Authors: Ramakrishna, Shreyas, Rahiminasab, Zahra, Karsai, Gabor, Easwaran, Arvind
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Deep Neural Networks; Mutual Information Gap
• Online Access: https://hdl.handle.net/10356/163574
• Institution: Nanyang Technological University

Deep Neural Networks are actively being used in the design of autonomous Cyber-Physical Systems (CPSs). The advantage of these models is their ability to handle high-dimensional state-space and learn compact surrogate representations of the operational state spaces. However, the problem is that the...