We use Machine Learning, Artificial Intelligence, and Crowdsourcing to understand how large groups of people design things and how complex engineered systems work, so that we can use the data they produce to make them better.

Some of the fundamental scientific questions we study include: What are efficient and useful ways to computationally and mathematically represent designs? How do we combine physics-driven and data-driven models to design better products? What makes design collaboration between large groups of people work well or poorly? How can we use tools from applied mathematics (such as graph theory, category theory, and statistics) and computer science (such as complexity theory, submodular optimization, and artificial intelligence) to better understand how humans design?

Some past practical applications of our research include: a fully automated system for inferring what makes designs creative given human feedback; the world’s first polynomial time algorithm for diverse bi-partite b-matching; algorithms for exploring and optimizing high-dimensional design spaces (e.g., aircraft); software for helping novices 3D print working mechanical devices; and network analyses of online collaborative design networks such as OpenIDEO.

You can read more about our work by looking at our papers or by reproducing any of our open-source code.

Citrine Informatics featured our new Pre-Print “Applying machine learning techniques to predict the properties of energetic materials” in the “New Literature Worth Reading” section of its Data-Driven Material Science and Chemistry Newsletter!

Posted 22 Jan 2018 by Mark

Our article entitled “Active expansion sampling for learning feasible domains in an unbounded input space” was published in Structural and Multidisciplinary Optimization (SAMO). Check out the publications page for more information.

Posted 19 Jan 2018 by

Mark was recently a guest on the IBM Business of Government hour, where he discussed the IDEAL lab’s work, the future of Data-Driven Design, and some of the challenges it faces. You can listen to the podcast here.

Posted 14 Dec 2017 by Mark

Dr. Mark Fuge is leading a UMD team recently awarded a project as part of the DARPA Fundamentals of Design (FUN DESIGN) program for a project entitled “Learning to Move: From Operads to Fields to Functioning Topologies”. The project explores how techniques from Category Theory, Reinforcement Learning, and Functional Programming can fundamentally re-think and automatically re-discover how conceptual design of mechanical systems works.

Posted 06 Nov 2017 by Mark
Published 22 Jan 2018
Published 19 Jan 2018
Creative Exploration Using Topic Based Bisociative Networks
Faez Ahmed and Mark Fuge Design Science 2018
Published 05 Jan 2018
Ranking ideas for diversity and quality
Faez Ahmed and Mark Fuge JMD 2017
Published 01 Sep 2017
Diverse Weighted Bipartite b-Matching
Faez Ahmed, John P. Dickerson and Mark Fuge IJCAI 2017
Published 23 Aug 2017