I have recently encountered the term "generative design" where a computer algorithm (usually with the help of Machine Learning) comes up with new designs that conform to a certain set of requirements. These designs are usually more intricate while also being lighter and stronger than what humans would design.

I would like to get deeper into the topic, however I can mostly only find offerings (from AutoDesk etc.) instead of a good description on how exactly it works (or even a mathematical description). Could you please point me to some studies, articles or any sources where I could delve into the topic?


This is often called algorithmic design or optimal design. The last name hints on some optimality criteria, and there are many to choose from! Much used is D-optimality. Some related posts here is Motivations for experiment design in statistical learning? and Is DoE applicable to collect data for machine learning model?, look at the links and references in there.

There are many published books on the topic, one place to start could be Optimal Experimental Design with R. Bayesian ideas could also be useful. This stored search might be useful.

Alternatively, if your question is more about product design, you could try to ask at https://or.stackexchange.com/. Links/papers about machine learning and generative design.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.