Beyond Grepping: Classical Computing Solutions or
Deep-Learning for Root Cause Analysis of Log-files
Speaker (s):
Mika Mäntylä
Professor
University of Helsinki
|
|
Date:
Time:
Venue:
|
|
5 October 2023, Thursday
2:00pm – 3:00pm
School of Economics/School of Computing
& Information Systems 2 (SOE/SCIS 2)
Level 4, Seminar Room 4-2
Singapore Management University
90 Stamford Road, Singapore 178903
Please register by 4 October 2023.
We look forward to seeing you at this research seminar.
|
|
About the Talk
Identifying root causes of failures from log-files is a challenging task. In the face of vast volumes of log data generated by software, industry professionals traditionally resort to their domain knowledge to create keywords for 'grepping' through log files. Recently, the academic community has been keen on applying deep-learning for log anomaly detection. However, deep-learning can often be complex and costly to train. With their simplicity and efficiency, classical computing may be more practical and feasible for industrial collaboration. Thus, a conflict rises between industrial demand for speed and utility versus academic demand for excellence.
About the Speaker
Mika Mäntylä is a professor of Software Engineering at the University of Helsinki and University of Oulu, Finland. He received a D. Sc. degree in 2009 in Software Engineering from Aalto University, Finland. His research interests include end-of-lifecycle software engineering activities like software testing, maintenance, and operations. He is also interested in research methods, meta-science, and behavioral and psychological aspects in software engineering. He is keen to utilize natural language processing, classical machine learning, and deep learning for software engineering problems. He has worked as an assistant professor at Aalto University, Finland, and as a post-doc at Lund University, Sweden. He is an associated editor for IEEE Software magazine and Empirical Software Engineering journal. For more information, https://mmantyla.github.io.
