NCSU SE 426/526
Spring 2026.
AI presents unique challenges and opportunities when applied to software engineering. Unlike other domains, SE involves evolving requirements, human-in-the-loop decisions, and complex socio-technical ecosystems, making the integration of AI both powerful and precarious. This course will explore AI methods for SE, such as explainable AI, classification and clustering, multi-objective optimization, semi-supervised learning (useful when labeled data is scarce), theorem proving and logical reasoning, and generative methods enable code suggestion, test generation, and documentation support.
426 and 526:
- Students will apply sound research methods/tools to problems in “AI to SE” and “SE to AI” and describe the methods/tools effectively
- Students will analyze/interpret research data
- Students will communicate their research clearly and professionally in both written and oral forms appropriate to “AI to SE” and “SE to AI”
526:
- State a research problem in such a way that it clearly fits within the context of the literature in “AI to SE” and “SE to AI”
- Demonstrate the value of a research solution to the research problem in advancing knowledge within that area
Tim Menzies (Ph.D. UNSW 1995, ACM Fellow, IEEE Fellow, ASE Fellow) is a globally recognized leader in software engineering research, best known for his pioneering work in data-driven, explainable, and minimal AI for software systems. Over the past two decades, his contributions have redefined defect prediction, effort estimation, and multi-objective optimization, emphasizing transparency and reproducibility.
As the co-creator of the PROMISE repository, Prof. Menzies helped establish modern empirical software engineering, showing that small, interpretable AI models can outperform larger, more complex ones. Currently, he works as a full Professor in computer science at NC State, USA. He is the director of the Irrational Research lab (mad scientists r'us). His research has earned over** $19+ million** in funding from agencies such as NSF, DARPA, and NASA, as well as from private companies like Meta, Microsoft and IBM.
Prof. Menzies has published over 300 papers, with more than 24,000 citations, and advised 24 Ph.D. students. He is the editor-in-chief of the Automated Software Engineering journal and an associate editor for IEEE TSE. His work continues to shape the future of software engineering, focusing on creating AI tools that are not only intelligent but also fair, transparent, and trustworthy. For more information, visit http://timm.fyi.