Skip to content Skip to main navigation Report an accessibility issue

AI in Complex Systems Lab


The AI in Complex Systems Lab aims to advance the science of artificial intelligence (AI) and address the prominent existing gaps and challenges in AI methods and their translation to practice. The application areas include, but are not limited to, health care, genomics, advanced manufacturing, intelligent transportation systems, environment, nuclear energy, and cybersecurity, among others. The methodologies include, but are not limited to,

  • Predictive Analytics
  • Reinforcement learning
  • Clustering
  • Understanding and mitigating bias in AI
  • Variational and Bayesian inference for learning from limited data
  • Generative adversarial learning
  • Physics-informed learning
  • Human-in-the-loop learning
  • Active learning
  • Explainable AI (XAI)


Affiliated Faculty Members