Safety and reliability of deep learning: (Brief overview)

Huang, X ORCID: 0000-0001-6267-0366 (2021) Safety and reliability of deep learning: (Brief overview) In: CPS-IoT Week '21: Cyber-Physical Systems and Internet of Things Week 2021.

Text main_arxiv.pdf - Submitted version Download (823kB) | Preview

Abstract

Robotics and Autonomous Systems (RAS) become ever more relying on deep learning components to support their perception and decision making. Given RAS will inevitably be applied to safety critical applications, efforts are needed to ensure that the deep learning is safe and reliable. In this lecture, I will give a brief overview on recent progress in the verification and validation techniques for deep learning, focusing on two major safety and reliability risks, i.e., robustness and generalisation. We consider formal verification, statistical evaluation, reliability assessment, and runtime monitoring techniques, all of which complement with each other in providing assurance to the reliability of deep learning in operation. The challenges and future directions will also be discussed.

Item Type:	Conference Item (Unspecified)
Uncontrolled Keywords:	4613 Theory Of Computation, 46 Information and Computing Sciences, Machine Learning and Artificial Intelligence, Networking and Information Technology R&D (NITRD)
Divisions:	Faculty of Science & Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	29 Sep 2021 08:06
Last Modified:	24 Jan 2026 03:08
DOI:	10.1145/3459086.3459636
Related Websites:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3138591
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.