ICIIS 2021

Tutorial on Explainable Machine Learning

11th of December 2021

Scope

Introduce the basics of explainability and tools for the same.

Target Audience

Postgraudate Students, Researchers, Industry, Decision/Policy makers, Undergraduate students

Introduction:

Machine Learning is an effective tool that can and has been used in high-stakes decision-making. Thereby, automated decision making based on ML tools with effects on individuals and the society demands better understanding of them (ML tools) and their behaviours.
Can black box models cater to that demand? Can we trust them and if yes, how much?
This tutorial is aimed to (i) introduce the models/methods for explainability of Machine Learning models (ii) provide hands-on in tools for the same and (iii) discuss prospects of applications of mentioned methods. This tutorial will especially be useful for industry professionals, researchers, policy makers, postgraduate and undergraduate students seeking further research on this topic.

Facilitators:

Dr Kasun Amarasinghe, Carnegie Mellon University Pittsburgh PA, USA Kasun Amarasinghe received the B.Sc. degree in computer science from the University of Peradeniya, Sri Lanka, in 2011, and the Ph.D. degree in computer science from Virginia Commonwealth University, Richmond, USA, in 2019. He is currently a Postdoctoral Research Associate at Carnegie Mellon University (CMU). His research interests include explainable machine learning, algorithmic fairness, and applications of machine learning in the domain of public policy.


Dr Damayanthi Herath, Department of Computer Engineering, University of Peradeniya, Sri Lanka Damayanthi Herath graduated with a B.Sc. (Hons) in Computer Engineering, University of Peradeniya in year 2012 and is a member of IEEE. She was a member of the Optimisation and Pattern Recognition Research Group of Melbourne School of Engineering, Australia where she worked on computational models and methods to profile inherently diverse DNA sequencing data which encode genetic information of multiple species and organisms. She is currently a senior lecturer at Department of Computer Engineering, University of Peradeniya. Her research interests are in applied machine learning, especially in areas with social impact/aspect.





Eng. Shyaman Jayasundara, Agricultural Biotechnology Centre, University of Peradeniya, Sri Lanka Shyaman received the B.Sc. degree in Computer Engineering from the University of Peradeniya, Sri Lanka, in 2020. He is currently a full-time Research Assistant at the Agricultural Biotechnology Centre at the University of Peradeniya. His research interests include machine learning applications in bioinformatics and health informatics.


Eng. Amila Indika, Department of Computer Engineering, University of Peradeniya, Sri Lanka Amila Indika graduated with a B.Sc. (Hons) in Computer Engineering, University of Peradeniya, Sri Lanka, in 2020. He is currently employed as a lecturer on contract at Department of Computer Engineering, University of Peradeniya. His research interests are in applied machine learning, time-series analysis, and mathematics.