Currently pursuing a Ph.D. in Computer Science. Abeysinghe earned his Bachelor of Science in Computer Science from the University of Peradeniya, Sri Lanka.
Abeysinghe's expertise is in Parallel Computing, Artificial Neural Network and Artificial Intelligence. He has experience creating CNN, FCNN and other SOTA classification and detection models. His also has experience working with logistic regression, Naive Bayes classifier and SVM. His research framework also includes: Model selection mechanisms as Cross validation and Grid search, SLURM computer clusters, Apache Spark, as well as GNU/Linux systems
Abeysinghe is a member of the Free Software Foundation and speaks fluent English and Sinhala.
Research and Published Studies:
Abeysinghe, T. M, M. B., Gunethilaka, B.B.J., Nawarathna, R.D. (2016). “Opinion Mining on Various Aspects of Health Through Social Media Analytics Using Collective Sentiment Feature Analysis and Deep Neural Networks” University of Peradeniya. Sri Lanka. Proceedings iPurse.
Alumni Prize for Excellence in Computer Science, University of Peradeniya, National Department of Statistics and Computer Science. (2017)
Abeysinghe’s research framework includes social media analytics with a concentration in Natural Language Processing used in classifying tweets. His work explores the domains of Artificial Intelligence and Expert Systems. That includes: Neural Language Model, Recurrent Neural Networks in Language and Artificial General Intelligence.
Abeysinghe’s ongoing research has been testing different models of Deep Neural Networks such as Recurrent Neural Networks (RNN), Gated Recurrent Units (GRUs), Long Short Term Memory (LSTM) models, Convolutional Neural Networks (CNN) and Fully Convolutional Neural Networks (FCNNs). He then gauges the behavior and performance in different environmental conditions.
During his time as a lecturer at the University of Peradeniya, Abeysinghe taught Structure Oriented Programming, Image Processing Practical Data Structures and Computer Graphics.