Disentangling latent space of variational autoencoder with distribution dependent guarantees for out-of-distribution detection and reasoning

Disentangling latent space of variational autoencoder with distribution dependent guarantees for out-of-distribution detection and reasoning

Cyber-physical systems (CPS) have diverse applications, especially in a safety-critical setting, such as autonomous cars (AV). In safety-critical systems, any mistake can lead to non-compensable results, such as losing individuals. Therefore, ensuring the safety of such systems is vital. Many saf...

Full description

Bibliographic Details
Main Author: Rahiminasab Zahra Reza (Zahra Rahiminasab)
Other Authors: Arvind Easwaran
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2024
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Online Access:https://hdl.handle.net/10356/172959

Internet

https://hdl.handle.net/10356/172959

Similar Items