Design Computation & Digital Engineering Lab

DeCoDE Lab is based in the Mechanical Engineering department at MIT. Our vision is to create a world where humans and AI design together to solve our biggest challenges. We use Machine Learning and Optimization methods to enable better design of complex mechanical systems and assist teams of human designers to transcend their potential.

Our work lies at the intersections of Mechanical Engineering, Artificial Intelligence, and Human-Computer Interaction. A few questions we are interested in: How can we synthesize or discover new designs which have never been seen before? How can we enable distributed teams of people to create new products? How can we design, develop, and deploy advanced engineering material systems for complex non-linear inverse problems? How can we allocate people to teams to maximize efficiency? How can we quickly and reliably measure the creativity of thousands of ideas? How can we filter useful ideas out of hundreds of submissions? While these questions address different areas, our underlying approach is to mathematically characterize these questions as generalizable machine learning and optimization problems, make testable predictions for new problems, and tie together or understand individual empirical results that researchers have generated.

The techniques we study apply to a wide range of problems in Engineering. We aim at transforming the way humans design products and measure our success by the impact of our work on society. We believe in reproducible and open-source science whenever possible, and do our part by making most of our research code and papers available online.




Selected Publications [See all]


Chen, W., Ahmed, F.
PaDGAN: Learning to Generate High-Quality Novel Designs
In Journal of Mechanical Design 2020
PDF     Project Page

Wang, L., Chan, Y., Ahmed, F., Liu, Z., Zhu, P., Chen, W.
Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems
In Computer Methods in Applied Mechanics and Engineering 2020
PDF    

Chan, Y., Ahmed, F., Wang, L., Chen, W.
METASET: Exploring Shape and Property Spaces for Data-Driven Metamaterials Design
In Journal of Mechanical Design 2020
PDF     Dataset

Ahmadi, S., Ahmed, F., Dickerson, J., Fuge, M., Khuller, S.
An Algorithm for Multi-Attribute Diverse Matching
In IJCAI 2020
PDF     Project Page

Cui, Y., Ahmed, F., Sha, Z., Wang, L., Fu, Y., Chen, W.
A Weighted Network Modeling Approach for Analyzing Product Competition
In IDETC 2020
PDF    

Ahmed, F., Dickerson, J., Fuge, M.
Forming Diverse Teams from Sequentially Arriving People
In Journal of Mechanical Design 2020
PDF     Project Page

Principal Investigator


Faez Ahmed

Assistant Professor
Department of Mechanical Engineering
Massachusetts Institute of Technology
Email: faez at mit dot edu


Current Members



Amin Heyrani Nobari
Amin Heyrani Nobari

Amin Heyrani Nobari

Graduate Student

ahnobari@mit.edu

Kristen Edwards
Kristen Edwards

Kristen Edwards

Graduate Student

kme@mit.edu

Lyle Regenwetter
Lyle Regenwetter

Lyle Regenwetter

Graduate Student

regenwet@mit.edu

Vaishnavi L Addala
Vaishnavi L Addala

Vaishnavi L Addala

UROP

vaddala9@mit.edu

Alumni



Sabiyyah Ali
Sabiyyah Ali

Sabiyyah Ali

UROP

sabi@mit.edu

Kristopher L Vu
Kristopher L Vu

Kristopher L Vu

UROP

krisvu@mit.edu

Melory So
Melory So

Melory So

UROP

melory@mit.edu

News




Talks & Travel


15th Oct - Faez gave a virtual talk at Intel Corporation's IT R&D team.

6th Oct - Faez gave a seminar on "Automated discovery of high-quality novel designs" at the APETS Symposium.

30th Sep - Faez gave a seminar at the MIT MechE Alliance.

11th May - Faez gave a virtual seminar at Autodesk Research, hosted by Dr. Hyunmin Cheong.



Announcements


Prospective Ph.D. students - MechE at MIT admits students to the department itself, not to an individual advisor. If you are an already-admitted student at MIT, feel free to get in touch.

If you are interested in joining the DeCoDE lab, drop me an email with the following text in your subject line "Join DeCoDE:" followed by the position you are interested in (for example, a postdoc, intern, visiting researcher, etc.).