Postgraduate Certificate in AI Trustworthiness Assessment and Implementation

• AI Ethics and Governance: This unit covers the ethical principles that guide AI development and implementation, including fairness, accountability, transparency, and privacy. It also explores the legal and regulatory frameworks that govern AI use.

• AI Trustworthiness Metrics: This unit introduces various metrics for assessing AI trustworthiness, such as explainability, robustness, and security. It also covers the challenges in developing and applying these metrics.

• AI Bias and Discrimination: This unit examines the sources and consequences of AI bias and discrimination, including algorithmic, data, and human biases. It also presents methods for mitigating these biases and ensuring fairness in AI systems.

• AI Explainability and Interpretability: This unit delves into the techniques for explaining and interpreting AI models and decisions, such as feature importance, partial dependence plots, and LIME. It also discusses the trade-offs between accuracy and interpretability.

• AI Robustness and Security: This unit explores the methods for ensuring AI robustness and security, including adversarial attacks, defensive distillation, and model hardening. It also covers the risks of AI system failures and cyber threats.

• AI Human-Machine Collaboration: This unit investigates the ways of designing and implementing AI systems that augment human capabilities and foster trust and collaboration. It also discusses the challenges and opportunities of human-AI teaming in various domains.

• AI Evaluation and Validation: This unit presents the methods for evaluating and validating AI systems, including statistical testing, simulation, and user studies. It also covers the challenges in assessing AI performance and comparing it to human performance.

• AI Societal Impact and Responsibility: This unit discusses the broader social and economic implications of AI, including job displacement, income inequality, and social sorting. It also highlights the ethical and legal responsibilities of AI developers and users.