GNE336 Trustworthy and Secure AI

[3–0, 3 cr.]

This course provides an introduction to validating, tuning, and assuring machine learning and neural network algorithms, among other categories of AI algorithms. The course targets AI assurance, bias mitigation, AI explainability, trustworthiness, data poisoning, and imbalance issues. Additionally, it will cover topics relevant to security and privacy within AI systems, including: detecting and mitigating cyber threats, cyber hygiene, protecting big data, and cyber policies. AI and cyber application examples are presented and studied, such as applications in the policy, medical, biological, water, and agricultural domains, amongst others.