This course covers the practical use of Generative Artificial Intelligence (GenAI) as a research support tool in engineering and scientific disciplines, with a strong emphasis on hands-on applications. The course introduces the capabilities, limitations, and effective use of modern generative AI systems, including large language models, multimodal models, and AI-assisted development environments, within real research workflows. Core content includes applied prompt engineering, AI-assisted literature review, automated knowledge synthesis, and research problem formulation using generative AI tools. Students will explore how to integrate AI into key stages of the research lifecycle, such as coding support, experimental prototyping, data preprocessing, synthetic data generation, and technical documentation. Practical implementation of retrieval-augmented generation (RAG) and domain-specific AI tool usage for engineering and computational research will also be addressed.

Course Objectives

The main objective of this course is to provide scientists with practical and research-oriented competencies in the effective use of Generative Artificial Intelligence (GenAI) within engineering and scientific research environments. The course aims to bridge theoretical knowledge and real-world application by focusing on how generative AI can be systematically integrated into the graduate research process. Another key objective is to enable scientists to utilize modern generative AI tools to support core research activities such as literature review, research problem formulation, coding, experimentation, data processing, and technical reporting. The course is designed to develop applied skills that directly enhance students’ thesis and project workflows through AI-augmented methodologies. The course also aims to foster interdisciplinary problem-solving by demonstrating how generative AI technologies can be adapted to diverse research domains within engineering and natural sciences. Emphasis is placed on hands-on tool usage, reproducible experimentation, and the development of end-to-end AI-assisted research pipelines.

Course Resources

Raschka, S. (2024). Build a Large Language Model (From Scratch). Manning Publications.

Foster, D. (2022). Generative Deep Learning (2nd ed.). O’Reilly Media.

Prince, S. J. D. (2023). Understanding Deep Learning. MIT Press.

Planned Learning Activities and Teaching Methods

The course will be delivered through an application-driven and project-based teaching methodology that prioritizes hands-on learning over theory-intensive instruction. Short conceptual lectures will be used to introduce essential topics in generative artificial intelligence, followed by extensive practical sessions where students actively apply AI tools to real research tasks in engineering and scientific domains. Learning activities will include guided hands-on labs, live demonstrations, and tool-based workshops focusing on the use of large language models, retrieval-augmented systems, multimodal AI tools, and AI-assisted coding environments. Students will engage in structured in-class exercises such as AI-assisted literature review, research problem formulation, experimental prototyping, data processing, and technical report generation using modern generative AI platforms. Interdisciplinary case studies will be incorporated throughout the course to demonstrate how generative AI can be utilized across different research areas, including engineering, natural sciences, and computational research. Interactive discussions and problem-based learning activities will encourage students to adapt generative AI tools to their own scientific research topics and domain-specific research needs.

Grading

Homeworks (2) : 20%
Project : 20%
Midterm Exam: 20%
Final Exam: 40%

Course Learning Outcomes

The students who succeeded in this course will be able to:

• Effectively use state-of-the-art generative AI tools and frameworks (e.g., LLMs, multimodal models, and AI development environments) to support research and problem-solving in engineering and scientific domains.
• Design and implement practical AI-augmented research workflows that integrate generative AI into literature review, data analysis, experimentation, coding, and technical documentation processes.
• Apply generative AI techniques to interdisciplinary research problems by adapting AI tools to domain-specific tasks such as modelling, simulation support, data processing, and research prototyping.
• Use generative artificial intelligence in a responsible, ethical, and transparent manner in graduate-level research, ensuring academic integrity and proper documentation of AI-assisted methodologies.