- PhD Student
About me
I'm pursuing a PhD at the University of Cambridge, exploring the potential of federated learning for various applications. In simpler terms, federated learning allows multiple devices to train a machine learning model collaboratively without sharing private data. This is a powerful approach for tasks like improving healthcare diagnostics or optimizing energy usage in smart grids, where data privacy is paramount.
Previously
I am a founding member of DeepNano, a nanoelectronics research team at the University of Glasgow. One of my key contributions was the creation of ML-NEGF, a novel simulation approach that merges machine learning with non-equilibrium Green's function (NEGF) simulations.
ML-NEGF leverages a convolutional generative network to "learn" the underlying physics governing nanosheet transistors. It can significantly accelerate the design and optimization of nanoelectronic devices, leading to faster analyses in fields like high-performance computing, energy harvesting, and quantum technologies.
Beyond my academic pursuits, I'm also actively involved in engineering. As a research software engineer at MoFEM, I developed integrations between MoFEM modules and FreeCAD. This consists of using my machine learning and electronics knowledge to create tools to streamline the design and simulation of complex engineering systems.
