Sahan Bulathwela (IN4MANIAC)

AI Researcher

University College London


Sahan is affiliated to the UCL Centre for Artificial Intelligence currently contributing to the X5GON project and HumaneAI project working with Prof. Emine Yilmaz and Prof. John Shawe-Taylor. His research interests lie on the theme: “Improving Recommendations of Educational Contents to Lifelong Learners”. Before joining UCL, he worked in several research roles in the industry in cybersecurity and personalised advertising domains where he gained experience in user state modelling in a big data landscape.


  • AI in Education
  • Recommendation Systems
  • Bayesian Statistics
  • Artificial Intelligence


  • PhD in Artificial Intelligence, Ongoing

    University College London, UK

  • MSc in Computational Statistics and Machine Learning, 2014

    University College London, UK

  • PGDip in Applied Statistics, 2012

    University of Peradeniya, Sri Lanka

  • BSc (Hons.) in Computing, 2010

    University of Portsmouth, UK


Artificial Intelligence








Research Assistant

University College London (X5GON Project)

Apr 2018 – Present London

X5GON project (https://www.x5gon.org) envisions to leverage a Cross Modal, Cross Cultural, Cross Lingual, Cross Domain, and Cross Site Global Open Educational Resource Network for informal learners.

Main responsibilities include: - Conducting deep research and execute well designed experiments leading to inventing novel methods in improving informal learners’ learning trajectories. - Deriving automatic quality assessment models for educational resources - Deriving rich representations of knowledge and its learners - Deriving intelligent models for personalized recommendation of educational materials.


Senior Teaching Fellow

CambridgeSpark Ltd.

Sep 2016 – Present London/ Cambridge
Course development and review. Teaching and training professionals and university students in knowledge areas related to Machine Learning and Data Science. Courses created and taught: - Database Management Systems and Cloud Computing - Big Data and Distributed Computing - Exploratory Data Analysis and Machine Learning - Neural Networks Employers of past students: - JP Morgan Chase & Co - Morgan Stanley - Cambridge Centre for Alternative Finance - Schlumberger Cambridge Research Centre and etc…

Data Science Engineer


Sep 2015 – Mar 2018 London
Main responsibilities included: - Primary focus on New Product and Advanced Development with Research towards building innovative data products for Strategic growth - Mainly responsible for bridging the cutting edge data science and machine learning with HPC and distributed computing - Designing high performance data structures to enable teams to get the most out of TBs of data that pumps in to the systems on daily basis - Designing and Building massively parrallel, high performance data pipelines that utilise state of the art data structures, compression and machine learning algorithms


API Winner : StoryTunes

Based on an article URL provided by the user we get the text, title, keywords and entities from the Alchemy API. We use the musiXmatch lyrics dataset of the million song dataset (http://labrosa.ee.columbia.edu/millionsong/challenge) to generate a list of topic cluster of the available songs. Using the Alchemy information we then classify the article to one of this topics and retrieve the nearest songs. In addition we use the article entities to retrieve top songs directly from music APIs. Those combined results are then surfaced on the front end.

CIIP Research Fellowship

Cisco International Internship Programme (CIIP) is a programme for UCL students to conduct a one year research fellowship with a Research and Advanced Development team at Cisco Systems. One of the three students selected for the fellowship in 2013

UCL Advances Research Fellowship (Awarded Twice)

UCL Advances research fellowship is a scheme for UCL students to conduct bleeding edge research with Startup companies in London.

Recent Posts


Recent & Upcoming Talks

Recent Publications

Quickly discover relevant content by filtering publications.

Predicting Engagement in Video Lectures

Open Education Resources (OERs) have increased significantly in the last decade, giving learners access to a wider range of educational …

What's in it for me? Augmenting Recommended Learning Resources with Navigable Annotations

This paper introduces an interface that enables the user to quickly identify relevant fragments within multiple long documents. The …

SUM'20: State-based User Modelling

Capturing and effectively utilising user states and goals is becoming a timely challenge for successfully leveraging intelligent and …

Towards an Integrative Educational Recommender for Lifelong Learners

One of the most ambitious use cases of computer-assisted learning is to build a recommendation system for lifelong learning. Most …

TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources

The recent advances in computer-assisted learning systems and the availability of open educational resources today promise a pathway to …

Popular Topics


  • 90 High Holborn, London, WC1V 6LJ
  • Enter Building and take the lift to 1st Floor
  • DM Me
  • Skype Me