Research on deep transformer-based symbolic regression for interpretable modeling of gravitational wave signals
Research Vision
My end quest is to create a tool that will be theoretical scientists' best friend: analyze natural science data and come up with ways to represent it mathematically, and consistently. As experiments grow more complex, interpreting data becomes increasingly difficult. AI, one of the 21st century's most powerful tools, can assist in recognizing patterns beyond human capability and help us advance our scientific discovery process.
What I want to focus on is the recently emerging field of delving into more of the mathematical side, creating theoretical structures with the help of artificial intelligence, thereby getting humanity closer to fundamental theories.
I believe that as scientists, we have a responsibility to choose how we spend our time for projects that help people and make the world better, not harm it. Human wellbeing should always come first in our work.
Research Projects
Deep learning models for predicting quantum system dimensions and Hamiltonian parameters from minimal measurement data
Investigating mutual information as a proxy to predict the difficulty of learning wave functions using Neural Quantum States in quantum many-body systems
Implementing physics-informed neural networks to learn theoretical quantities like the Lagrangian from trajectory data using symbolic regression