Degree

Master of Science in Computer Science

Department

Department of Computer Science

Faculty / School

Faculty of Computer Sciences (FCS)

Date of Submission

2023-11-21

Supervisor

Waqas Mahmood, Visiting Faculty, Department of Computer Science, School of Mathematics and Computer Science (SMCS)

Document type

MSCS Survey Report

Keywords

Machine Learning, Machine Learning Testing, Software Testing, Software Quality Assurance, Reliability Engineering

Abstract

Machine learning has become widespread across several domains. It has its applications in mission critical and safety critical applications, which makes it imperative to assure its correctness and trustworthiness (reliability and robustness) properties. Software verification and testing is an established technique for assuring such properties. However, software testing challenges for machine learning are different in nature, as opposed to traditional software systems. In this paper, current approaches to these challenges are discussed along with the necessary testing properties to establish the quality of machine learning applications. We’ve also investigated how reliable Machine Learning system themselves and are they conducive for mission critical and safety critical applications.

The full text of this document is only accessible to authorized users.

Share

COinS