Assured autonomy in safety critical CPS

The aim of this study is to investigate safety guarantees on variational autoencoder (VAE) outputs. The problem of establishing a safety guarantee on machine learning models is to ensure that the model probabilistically satisfies particular constraints. The model targeted in this study is the β-VAE,...

Täydet tiedot

Bibliografiset tiedot
Päätekijä: Prashant, Mohit
Muut tekijät: Arvind Easwaran
Aineistotyyppi: Final Year Project (FYP)
Kieli:English
Julkaistu: Nanyang Technological University 2021
Aiheet:
Linkit:https://hdl.handle.net/10356/153289