Machine Learning in Design Research 2025-2026

Teacher: Dr. Guy Austern
Teaching Assistants: Bat-El Hizmi, Coral Hamo Goren

Machine Learning in Design Research explores how artificial intelligence can inform architectural design, research, and interpretation. Combining theoretical lectures, practical tutorials, and critical discussion, the course introduces students to machine learning through architectural data, images, and text. Students develop practical skills in Python and exploratory data analysis while learning about supervised and unsupervised learning, neural networks, computer vision, and natural language processing. Generative models and large language models extend this exploration to the production and interpretation of architectural content.

Through hands-on exercises, students learn to read and adapt basic code, work with existing models, adjust parameters, and formulate prompts for specific tasks. Emphasis is placed on understanding how computational models represent architectural information and critically evaluating the relevance and limitations of their outputs. The course culminates in an individual project in which each student develops a machine learning workflow to address an architectural question. By connecting technical experimentation with architectural judgment, the course equips students to make informed decisions about how and when to use machine learning in their work.