Biswajith Dissanayake is a Computer Departmental Lecturer at the Engineering Faculty, University
of Peradeniya. His work is at the intersection of generative modeling, probabilistic programming,
and deep learning, with an interest in applications of machine learning for scientific discovery.
He recently focused on Bayesian inference in large-scale simulators, implementing code for
distributed training and inference at supercomputing scale. Previously, He was an IT Specialist at
IBM World Trade Corporation working with telecommunications operations. Before his work at IBM, He
was a Lecturer at Uva Wellassa University and Peradeniya University CE Departments and Central
Engineering Counsultancy Bureau. In Russia, he specialized in differentiable programming and
worked on compositionality, higher-order functions, and nesting of forward and reverse
differentiation.
Computational analogy,
commonsense reasoning, and graph-based evolutionary algorithms.
End−to−End Optimization
of Stack Overflow with Differentiable Programming Toward the classification method with
Differentiable clusters
Bayesian Deep Learning
, Differentiable and Probabilistic Programming, Onboard cloud detection and atmospheric
correction with deep learning emulators
Research projects supervised by :
Predicting Cybersecurity Attacks Using Compound Analysis with Classification Algorithms
Please note that here only contain the
'Projects'
which were submitted to the
projects.ce.pdn.ac.lk
as
Final Year Research Projects
. The actual list of projects supervised by
may be longer than this.
Research Interests:
Data Science
Digital Image Processing
Internet of Things
Network-on-Chip
Software development
Project Management
Networking and Telecommunication
Optical Communication
Neural Networks
Edit Staff Profile Information
Profile
Update the details through
Staff Profile
editor in CE Portal.
Projects
This will be a automated process, if the students correctly configured the
project config file
Publications
You need to submit your publications (Only department affiliated and peer-reviewed
publications) through this
Google Form
.