My name is Khashayar Fathinejad. It is usually hard to pronounce, so I go by with Khash, altough I’m usually called something like cash, hash, or something similar.
I’m from Iran, specifically a city called Shiraz. It is known for many things, such as its rich history, poets, friendly people, and, yes, of course, wine.
I’m a PhD fellow at the Leiden Institute of Advanced Computer Science (LIACS) at Leiden University; I’m supervised by Wessel Kraaij, Mitra Baratchi, and Saber Salehkaleybar who are all based at LIACS.
For my bachelor’s, I studied Electrical Engineering, specializing in Control Systems, at Shiraz University, and then Computer Science – Decision and Knowledge Sciences track at the University of Tehran for my master’s degree.
During my master program, I wanted to do some research on the intersection of health and computer science, but it was not feasible, so finally, I settled on a topic that could be useful for health but in financial markets. My thesis was on Explainable AI in financial markets; I also did some research on Model Agnostic Meta-Learning in financial markets.
As I mentioned, I have always been passionate about contributing to people’s health and well-being. Thus, when I saw the opportunity to join LABDA, I didn’t hesitate. In this PhD program, I am able to combine my background in electrical engineering with the skills I gained in AI, all while making a meaningful contribution to health. It was a perfect opportunity to achieve multiple goals at once.
My PhD topic is “Interpretable causal machine learning for intervention development from wearable sensors data”. Causal machine learning is about understanding the causal mechanisms underlying the data. Understanding these mechanisms will equipe researchers with the knowledge to make predictions on how and how much we can affect some outcomes, design interventions, etc. One main point shapes my approach; many researchers in other fields lack the required knowledge of causal machine learning to use it in their field. So, we aim to create an automated framework to help them use it with minimal knowledge.
Every research is just a small part of something bigger. I’d be satisfied if, at any time, the methods we are developing to analyze accelerometer data would help to create healthier societies.
Within LABDA, I’m a part of the Diversity and Inclusion committee with Marian.
While I love mountains and heights, I chose to live in a country where the highest point, according to Wikipedia, is 322.4 meters!
