wir bieten...
Dekobild im Seitenkopf ISMLL
 
People: Randolf Scholz, M.Sc. Mathematics
Office hour:
C208 Spl, upon request
Phone, Fax, Email:
Phone: +49 5121 / 883-40370
Fax: n.a.
e-mail:
Postal address:
Information Systems and Machine Learning Lab
Universitätsplatz 1
University of Hildesheim
31141 Hildesheim
Germany
Visitor address:
Information Systems and Machine Learning Lab
Samelsonplatz 1
University of Hildesheim
31141 Hildesheim
Germany

Publications:

  • Vijaya Krishna Yalavarthi, Kiran Madhusudhanan, Randolf Scholz, Nourhan Ahmed, Johannes Burchert, Shayan Jawed, Stefan Born, Lars Schmidt-Thieme (2024):
    GraFITi: Graphs for Forecasting Irregularly Sampled Time SeriesTripletformer for Probabilistic Interpolation of Irregularly sampled Time Series, in Proceedings of the AAAI conference on artificial intelligence (AAAI, oral). PDF
  • Mesay Samuel Gondere, Lars Schmidt-Thieme, Durga Prasad Sharma, Randolf Scholz (2022):
    Multi-script handwritten digit recognition using multi-task learning., . PDF
  • Dr. Nghia Duong-Trung, Stefan Born, JongWoo Kim, Marie-Therese Schermeyer, Katharina Paulick, Maxim Borisyak, Ernesto Martinez, Mariano Nicolas Cruz-Bournazou, Randolf Scholz, Lars Schmidt-Thieme, Peter Neubauer,, Thorben Werner (2022):
    When Bioprocess Engineering Meets Machine Learning: A Survey from the Perspective of Automated Bioprocess Development, Biochemical Engineering Journal .
  • Raaghav Radhakrishnan, Jan Fabian Schmid, Randolf Scholz, Lars Schmidt-Thieme (2021):
    Deep Metric Learning for Ground Images, in arXiv preprint arXiv:2109.01569 (2021).
  • Mesay Samuel Gondere, Lars Schmidt-Thieme, Durga Prasad Sharma, Randolf Scholz (2022):
    Multi-script handwritten digit recognition using multi-task learning., in J. Intell. Fuzzy Syst., pp. 355-364. PDF
  • Randolf Scholz, Josif Grabocka, Lars Schmidt-Thieme (2019):
    Learning surrogate losses, in arXiv preprint arXiv:1905.10108 (2019).
  • Lukas Brinkmeyer, Rafael Rêgo Drumond, Randolf Scholz, Josif Grabocka, Lars Schmidt-Thieme (2019):
    Chameleon: Learning Model Initializations Across Tasks With Different Schemas, in arXiv preprint arXiv:1909.13576 (2019). PDF