Modern engineering is driven by computational workflows for modeling, simulation, and design. Machine learning methods show promise for augmenting engineering modeling, simulation and design across many application areas. Success stories from recent research include predicting the behavior of materials, using ML for physical simulation and design optimization, creating generative models of 3d objects and designs, optimizing energy systems to improve performance and reduce environmental impact, and many more.

This workshop aims to bring together the machine learning and engineering communities to foster collaboration and spur new research in the emerging field at their intersection. Broadly speaking, we are interested in work that develops or investigates machine learning methdos for application to engineering problems. Some ideas of specific topics we want to see addressed include, but are not limited to:

  • Learning surrogate and reduced-order models for physical simulators,
  • Using machine learning to accelerate design optimization, system identification and control,
  • Developing ML tools which can assist engineers to specify, explore and evaluate possible systems and designs,
  • Using ML to accelerate prototyping and manufacturing,
  • Integrating ML tools with preexisting engineering tools and workflows,
  • Development of software and libraries to enable all of the above,
  • Identification of applications and pressing challenges/opportunities in the application of ML to engineering.

Call for papers

We welcome submission papers on subjects related to the workshop topics consisting of:
  • Original completed research or high-quality work-in-progress
  • Investigations of open problems or important phenomena
  • Datasets or benchmarks
  • Position papers
  • Reviews/synthesis of recent work
  • Written tutorials or expositions of important concepts
  • Anything else relevant to our topics and of interest to the community
Relevant dates:
  • Submission deadline: Oct 05, 2020, anywhere on earth
  • Author notification: Oct 30, 2020
  • Deadline for SlidesLive video recording: Nov 14, 2020
  • Deadline for camera-ready paper: Nov 21, 2020

Submissions may be made via CMT at: https://cmt3.research.microsoft.com/ML4Eng2020.

Submissions should be short anonymized papers up to six pages (excluding references and supplementary materials) formatted according to the NeurIPS 2020 style. We encourage using fewer pages if you can. While you may submit supplementary material or appendices, all essential details should be in the main paper, as reviewers are not required to read this supplementary material. You should submit only one PDF, consisting of up to six pages of the main paper, followed by the references and then any supplementary materials / appendices.

Papers must not have been previously presented or accepted for presentation at an archival venue. However, this workshop is non-archival, and papers submitted to this workshop may be (concurrently or later) submitted to an archival venue.

Accepted works will be posted on this website (unless authors opt-out, in which case only the abstract will be posted), and will be presented as virtual posters, with an accopmanying 5-minute pre-recorded video. At least one author of each accepted work must register for the NeurIPS workshops and attend the virtual poster session.


To be confirmed.