Atri Sharma joined our group this October as a Safe and Trusted AI PhD student. We caught up with him to learn about his background and what he does in his spare time.
Where are you from, and what is your background?
I grew up in India and Singapore, following which I pursued an undergraduate degree in Aeronautical Engineering, also from Imperial College London. During the pandemic, I developed a strong interest in machine learning and applied it to optimise aircraft structures for weight and damage resistance in my master’s thesis.
I subsequently worked at a start-up applying machine learning to the healthcare domain, where I worked on research and deployment of Natural Language Processing algorithms on clinical data.
What influenced you to do a PhD, and what are your research interests?
Working in the healthcare domain highlighted a key problem within machine learning – it has an immense potential to identify at-risk patients, deliver improved, personalised care, and assist medical professionals. However, it has a low adoption rate in the real world due to a lack of trust. This lack of trust stems from a lack of explainability as well as observed fragility in predictions, which is difficult to understand, quantify, and subsequently mitigate. Therefore, I am interested in studying and developing machine learning algorithms that are verified and have certified performance guarantees so that they can be applied safely within sensitive use cases.
What do you do in your spare time?
I am a massive history buff (particularly aviation), and I really enjoy reading, watching documentaries, and going to museums. I love being active, with hiking and running being my favourite activities – I am working towards completing a marathon soon!
Furthermore, I greatly enjoy building and flying drones and model aircraft, and I have been part of and led several groups and competition teams in building and flying autonomous rotary and fixed wing aerial vehicles at school and university.