Machine Learning

Our research in machine learning addresses fundamental challenges in trustworthy AI. We develop formal methods for provably correct explanations, ensuring AI models are interpretable and accountable. Our work in reinforcement learning improves autonomous decisionmaking, while research on generalization and transfer learning enhances adaptability across tasks. We advance theory for uncertainty quantification and conformal prediction, improving reliability. Additionally, we explore the synergy between machine learning and quantum computing, driving the next generation of AI innovation.

<Back to main page