Nicolas Desmedt

Nicolas Desmedt

Brooklyn, New York, United States
1K followers 500+ connections

Join to view profile

About

Passionate builder. Thrive in uncertainty. Take the risk and fight for disproportionate…

Articles by Nicolas

Activity

Join now to see all activity

Experience

  • Whop Graphic

    Whop

    Brooklyn, New York, United States

  • -

    San Francisco, California, United States

  • -

    Lissabon, Portugal

  • -

    Lissabon, Portugal

  • -

  • -

    Leuven, Vlaanderen, België

  • -

    New York, New York, Verenigde Staten

  • -

    Leuven, Vlaanderen, België

  • -

    Leuven, Vlaanderen, België

  • -

    Brussel, Brussels Hoofdstedelijk Gewest, België

  • -

    Knokke, Vlaanderen, België

  • -

    Haasrode, Vlaanderen, België

Education

  • KU Leuven Graphic

    KU Leuven

    -

    Thesis: 'Active preference learning in product design decisions' at Flanders Make

  • -

    Activities and Societies: VTK

    General education for engineers the first year and a half, specialization in computer science and electrical engineering the final year and a half.

    Projects included the simulation of airplanes flying on autopilots and the construction of soft robots.

Publications

  • Active Preference Learning in Product Design Decisions

    Elsevier

    Master thesis turned scientific paper. This paper describes the benefits of using machine learning techniques to select the most promising product design concepts.

    Abstract:
    In the earliest product design stages, it can be challenging to decide which product concepts make the cut and are worth working out in more detail. Especially with the advent of technologies like concept generators that can generate a vast number of candidates, often a lot of assumptions are made when choosing…

    Master thesis turned scientific paper. This paper describes the benefits of using machine learning techniques to select the most promising product design concepts.

    Abstract:
    In the earliest product design stages, it can be challenging to decide which product concepts make the cut and are worth working out in more detail. Especially with the advent of technologies like concept generators that can generate a vast number of candidates, often a lot of assumptions are made when choosing the most promising candidates. While performance attributes can be simulated or otherwise estimated under different loads, it can be difficult to balance many desirable and undesirable performance attribute values. Here, active preference learning offers a solution methodology that leverages easy-to-give designer feedback to rank a large set of product concepts. Experimental evaluation of pertinent active preference learning algorithms demonstrates that accurate concept rankings can be learned given only minimal user effort, even when there is noise in the designer’s feedback. Moreover, this paper proposes and evaluates the use of a graph kernel to learn geometric preferences affecting the ranking, in addition to simulated performance attributes.

    Other authors
    See publication

More activity by Nicolas

View Nicolas’ full profile

  • See who you know in common
  • Get introduced
  • Contact Nicolas directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Nicolas Desmedt

1 other named Nicolas Desmedt is on LinkedIn

See others named Nicolas Desmedt

Add new skills with these courses

See all courses