Skip to content

CV

📰 PDF version

Education

  • [2017-2020] PhD in deep learning, Technical University of Denmark (DTU)
  • [2015-2017] Master in mathematical modelling and computation, Technical University of Denmark (DTU), GA: 11.0,
  • [2012-2015] Bachelor in mathematics and technology, Technical University of Denmark (DTU), GA: 10.5
  • [2010-2012] Higher technical exam (HTX), Roskilde Technical School, GA: 10.8

Work experience

  • 2022 - now: Postdoctoral Researcher,

    • Pioneer Centre for Artificial Intelligence
    • Research in MLOps and efficient machine learning. Teachning course 02476 Machine Learning Operations. Master and bachelor project supervision.
  • 2021 - 2022: Postdoctoral Researcher,

    • DTU Compute, Section for cognitive systems
    • Research in deep generative models and manifold learning. Teachning course 02476 Machine Learning Operations. Master and bachelor project supervision.
  • 2020 - now: Parttime software engineer

  • 2014 - 2017: Teaching assistant

    • DTU Compute
    • In course 02450 Introduction to machine learning and datamining. Support during exercises and correcting reports.
    • In course 01035 Mathematics 2. Support during exercises and correction of weekly handins.
  • 2013 - 2016: Part time research assistant

    • COWI
    • Data collection of public transportation patterns

Selected Publications

  • 2022

    • What is a meaningful representation of protein sequences?, Nicki Skafte Detlefsen, Søren Hauberg, Wouter Boomsma. In Nature Communications.
  • 2020

    • Lung Segmentation from Chest X-rays using Variational Data Imputation, Raghavendra Selvan, Erik B. Dam, Nicki S. Detlefsen, Sofus Rischel, Kaining Sheng, Mads Nielsen, Akshay Pai. In ICML Workshop on Learning from Missing Values (Artemiss). Arxiv link: https://arxiv.org/abs/2005.10052
  • 2019

    • Explicit Disentanglement of Appearance and Perspective in Generative Models, Nicki Skafte Detlefsen, Søren Hauberg. In Proceedings IEEE Conf. on Neural Information Processing Systems (Neurips), Vancouver, Canada. December 2019.

    • Reliable training and estimation of variance networks, Nicki Skafte Detlefsen, Martin Jørgensen, Søren Hauberg. In Proceedings IEEE Conf. on Neural Information Processing Systems (Neurips), Vancouver, Canada. December 2019.

    • Diffeomorphic Temporal Alignment Nets, Ron A. Shapira Weber, Matan Eyal, Nicki Skafte Detlefsen, Oren Shriki, Oren Freifeld. In Proceedings IEEE Conf. on Neural Information Processing Systems (Neurips), Vancouver, Canada. December 2019.

  • 2018

    • Deep Diffeomorphic Transformer Networks, Nicki Skafte Detlefsen, Oren Freifeld, Søren Hauberg. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA. July 2018.

Teaching

  • Machine Learning Operations

    Introduce the student to a number of coding practices that will help them organization, scale, monitor and deploy machine learning models either in a research or production setting. To provide hands-on experience with a number of frameworks, both local and in the cloud, for doing large scale machine learning models.

    Course webpage: https://skaftenicki.github.io/dtu_mlops/

    DTU course database: https://kurser.dtu.dk/course/02476

Skills

  • Language: Danish, English
  • Programming: Python, Matlab, C/C++, R, Maple, SAS
  • Programming frameworks: Pytorch, Tensorflow, CUDA, MPI