Artificial Intelligence

SEOR faculty are pioneering the integration of adaptive intelligence into engineering systems, with an emphasis on bridging the gap between "black-box" algorithms and mission-critical applications. 

Artificial Intelligence (AI) research priorities include explainable AI (XAI), deep learning, and Bayesian networks to ensure transparency and reliability in automated decision-making. Faculty specializes in uncertainty quantification for large language models and the deployment of distributed sensor networks within complex power systems.

SEOR researchers also leverage Multi-Entity Bayesian networks and causality inference to advance safety-aware reinforcement learning and manage partially observable Markov decision processes. These efforts culminate in the rigorous test and evaluation of intelligent systems, ensuring that interpretable machine learning remains robust for the demanding requirements of defense, aerospace, and global infrastructure.

Machine Learning

Research in machine learning focuses on developing interpretable and reliable models for complex engineering systems. Faculty integrate deep learning, Bayesian methods, and causality-driven approaches to enable robust, safety-aware decision-making under uncertainty, with applications in AI-enabled systems and defense and aerospace contexts.

Data Analytics

Faculty develop sophisticated methodologies to support decision-making under high degrees of uncertainty. This research integrates information fusion, data visualization, and uncertainty quantification to provide actionable insights in fields as diverse as plant breeding and public welfare.