Current AI models are used to either generate new data by recombining features of an input dataset or learn strategies to play video games. This research work aims to train such AI models for design applications by simulating three learning mechanisms: expertise, playfulness, and analogical reasoning. In design education, expertise is related to studying and analysing design precedents; playfulness is linked to model making; and analogical reasoning pertains to finding inspiration in domains other than architecture, such as nature, art, music, and literature. The research analyses what and how the AI models learn through various applications and describes interfaces that allow a designer to interact with the AI model through existing CAD software.
Please note that this talk will be delivered both in-person and online. Please select your preferred ticket type when registering. The zoom link will be included in the ticket confirmation email and in reminder emails.
Gabriele Mirra is an architect and computational design specialist with expertise in structural design, acoustics, robotics, and machine learning. He received his master’s degree in architecture from the University of Naples Federico II (Italy) in 2015. Between 2014 and 2018, he did research on structural and acoustic optimisation using Genetic Algorithms. He developed plugins for acoustic analysis – Aeolus – and the tessellation of freeform surfaces – GridMaker. In 2019 he started his PhD in AI in design at the Faculty of Architecture, Building and Planning of The University of Melbourne where he also teaches computational design and acoustics. His research explores new strategies to train AI models in architectural and structural design and integrate AI with CAD software to support the design process.