Mark Fuge

Principal investigator
CV
GitHub
Google Scholar
Email
fugeobfuscate@umd.edu

Mark Fuge is an Associate Professor of Mechanical Engineering at the University of Maryland, College Park, where he is also an affiliate faculty in the Institute for Systems Research and a member of the Maryland Robotics Center and Human-Computer Interaction Lab. His staff and students study fundamental scientific and mathematical questions behind how humans and computers can work together to design better complex engineered systems, from the molecular scale all the way to systems as large as aircraft and ships using tools from Computer Science (such as machine learning, artificial intelligence, and submodular optimization) and Applied Mathematics (such as graph theory, category theory, and statistics). He received his Ph.D. from UC Berkeley and has received an NSF CAREER Award, a DARPA Young Faculty Award, and a National Defense Science and Engineering Graduate (NDSEG) Fellowship. He gratefully acknowledges prior and current support from NSF, DARPA, ARPA-E, NIH, ONR, and Lockheed Martin, as well as the tireless efforts of his current and former graduate students and postdocs, upon whose coattails he has been graciously riding since 2015.

Papers

Effect of Optimal Geometries and Performance Parameters on Airfoil Latent Space Dimension

Mean Squared Error may lead you astray when Optimizing your Inverse Design methods

IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures

Learning Airfoil Manifolds with Optimal Transport

Inverse Design of 2D Airfoils using Conditional Generative Models and Surrogate Log-Likelihoods

Potential Energy Surfaces for Analysis and Conceptual Design and Analysis of Mechanical Systems

Automatically Discovering Mechanical Functions from Physical Behaviors Via Clustering

IH-GAN: A Conditional Generative Model for Implicit Surface-Based Inverse Design of Cellular Structures

Learning to Abstract and Compose Mechanical Device Function and Behavior

Airfoil Design Parameterization and Optimization using Bézier Generative Adversarial Networks

Forming Diverse Teams from Sequentially Arriving People

Machine Learning for Engineering Design

Algorithms for Optimal Diverse Matching

Using Semantic Fluency Models Improves Network Reconstruction Accuracy of Tacit Engineering Knowledge

Synthesizing Designs with Inter-part Dependencies Using Hierarchical Generative Adversarial Networks

Measuring and Optimizing Design Variety using Herfindahl Index

Checking the Automated Construction of Finite Element Simulations from Dirichlet Boundary Conditions

Structuring Online Dyads: Explanations Improve Creativity, Chats Lead to Convergence

Deep learning for molecular design - a review of the state of the art

Using natural language processing techniques to extract information on the properties and functionalities of energetic materials from large text corpora

Aerodynamic Design Optimization and Shape Exploration using Generative Adversarial Networks

Design creativity

Independent Vector Analysis for Data Fusion Prior to Molecular Property Prediction with Machine Learning

Interpreting Idea Maps: Pairwise comparisons reveal what makes ideas novel

Thermal Design and Testing of a Passive Helmet Heat Exchanger With Additively Manufactured Components

MGGD Parameter Estimation on the Space of SPD Matrices

BézierGAN: Automatic Generation of Smooth Curves from Interpretable Low-Dimensional Parameters

Machine Learning of Energetic Material Properties

Unpacking subjective creativity ratings : Using embeddings to explain and measure idea novelty

Synthesizing Designs with Inter-part Dependencies Using Hierarchical Generative Adversarial Networks

Applying machine learning techniques to predict the properties of energetic materials

Active Expansion Sampling for Learning Feasible Domains in an Unbounded Input Space

Creative Exploration Using Topic Based Bisociative Networks

Ranking ideas for diversity and quality

Diverse Weighted Bipartite b-Matching

Implications Of Data-driven Models For Design Theory And Methodology

Beyond the Known: Detecting Novel Feasible Domains over an Unbounded Design Space

Design Manifolds Capture the Intrinsic Complexity and Dimension of Design Spaces

Discovering diverse, high quality design ideas from a large corpus

How Designs Differ: Non-Linear Embeddings Illuminate Intrinsic Design Complexity

Capturing Winning Ideas in Online Design Communities

The MechProcessor: Helping Novices Design Printable Mechanisms Across Different Printers

A Scalpel not a Sword: On the Role of Statistical Tests in Design Cognition

Pattern Analysis of IDEO’s Human-Centered Design Methods in Developing Regions

Examining Design for Development Online: A Qualitative Analysis of OpenIDEO using HCD/UCD Metrics

How Online Design Communities Evolve Over Time: the Birth and Growth of OpenIDEO

User Research Methods for Development Engineering: A Study of Method Usage with IDEO's HCD Connect

Machine Learning Algorithms for Recommending Design Methods

Collaborative Design Informatics: Leveraging Data to Make Design Teams Better

Analysis of Collaborative Design Networks: A Case Study of OpenIDEO

Automatically Inferring Metrics for Design Creativity

ImpactMap: Designing Sustainable Supply Chains by Incorporating Data Uncertainty

CreativeIT Tools for Assisting and Evaluating Creativity and Problem Framing in Early-Stage Human-Centered Design

Conceptual Design and Modification of Freeform Surfaces using Dual Shape Representations in Augmented Reality Environments

Engineering Sketch Recognition: Findings from Recent Bio-Inspired and Cognitive Studies at VDEL

A Testing Method and Cognitive Model of Human Diagram Understanding for Automating Design Sketch Recognition

Posts

Year in Review: 2023

Year in Review: 2022

Year in Review: 2021

Year in Review: 2020

Year in Review: 2019

Prospective Student Frequently Asked Questions

Scientific Writing: A Self-Study Guide

Year in Review: 2018

Statement of Purpose Tips

Frequently Asked Questions