Likeness Trainer, 19th January - 15th March 2023
University of Cambridge and Microsoft
Candidates for Part IB of the Computer Science Tripos are required to undertake a group design project as part of their practical work in Lent term. The participants were Alex Matthews, Jonathan Haley, Jeffrey Song, Peter Isaksen, Tayo Oluranti-Ahmed and Tunan Shi. The project we worked on, is described below.
The human visual system is highly evolved to recognise faces even from a few lines. AI systems are improving, but we need more efficient tools to communicate which lines are meaningful to humans. The goal of this project is to create a tool for drawing the most essential lines onto photographed faces, as a starting point for psychological research into this fascinating human skill.
Presentation: GoogleDoc: Likeness Trainer.
Code: GitHub: Likeness Trainer
A video demo has been recorded to give a brief description of the project here:
Big Data Mauritius, 21st June - 25th June 2022
Hackathon tutors r to l; Dr Nikhita Madhanpall, David Bastien, Linxi Stirrup, Dr Zafiirah Hosenie & Dr Arrykrishna Mootoovaloo.
Awarding Best Presenter Prize to Love Achondo.
I was heavily involved in the organisation of the successful Big Data Mauritius 2022 event. The event took the form of a mini data science school, with a day of lectures from industry and academic speakers followed by a 3-day hackathon. I gave a talk ‘From Astronomy to Mixed Reality’, where I detailed my career journey to my current position at the Microsoft Mixed Reality and AI Lab in Cambridge. My talk was mostly about the futuristic work I am involved with at Microsoft, with projects including high-fidelity neural rendering for 3D object creation and the use of synthetic data to create realistic human faces and expressions.
During the hackathon, I provided support and advice to the participants. Everyone worked through several tutorials during the day using the cloud computing platform provided by IDIA. The next few days, they began to work on the hackathon task, which was to use data scraped from Twitter to analyse sentiment on a COVID19-related topic.
Africa Women in Data Science, 8 – 10 March 2022
DARA Big Data hosted its first African-focused Women in Data Science event. The event consisted of a one-day plenary session coinciding with International Women’s Day on Tuesday 8 March 2022, which additionally marks one year since the release of the SARAO Women in Data Science report.
Team 4 during our meeting and the topic they worked on during the hackathon.
Team 1 during our meeting and the topic they worked on during the hackathon.
This event was for women with a strong interest in data science from across the African continent. The one-day plenary was then followed by a hackathon event for female participants from the SKA Africa partner countries, which took place on the 9 and 10 March 2022. I acted as a mentor for two independent teams. I have tutored on topics of Data science and Natural Language processing and responded to all questions they have when implementing the code base.
3rd Big Data Africa School, Cape Town, 6 - 16 Oct 2019
The 3rd Big Data Africa School 2019, organised by SARAO, introduced fundamental data science tools and techniques to 25 talented young science and engineering graduates from South Africa and the 8 SKA Africa Partner countries. The School aims to develop student skills in working with extremely large datasets in any given research environment.
In the school, I was mentoring a group of students, working on sustainable agriculture project. Each day we brainstormed the project and split the tasks among the students. They worked over a period of six days to solve the assigned problems using real life datasets, culminating in a day where they presented their findings to a panel of experts and their fellow attendees.