My research focuses on developing mathematically principled learning algorithms for efficient training of artificial neural networks, with broad applicability across diverse architectures. I am particularly interested in algorithms enabling effective on-chip learning, which are essential for advancing embedded and neuromorphic computing systems. My long-term goal is to lay the theoretical and practical foundations for next-generation artificial intelligence, characterized by greater efficiency, scalability, and adaptability.

I completed my Bachelor of Science in Information and Computational Science at Tangshan Normal University (2014), with specialization in neural network application. Subsequently, I pursued graduate coursework in Computational Mathematics at North China Electric Power University (Beijing) before transitioning to Europe, where I earned a Master's degree through the joint Artificial Intelligence program between Vrije Universiteit Amsterdam and University of Amsterdam. From 2018 to 2022, I conducted doctoral research within the framework of a collaborative program in Electrical Engineering and Artificial Intelligence between Eindhoven University of Technology (TU/e), Centrum Wiskunde & Informatica (CWI), and imec. This research culminated in a dissertation and multiple publications in peer-reviewed journals and conference proceedings. Following the conferral of my doctorate, I served as a research scientist at Innatera Nanosystems until September 2024, focusing on neuromorphic computing applications.