Logo des Repositoriums

Auflistung nach Autor:in "Igel, Christian"

1 - 6 von 6
  • Zeitschriftenartikel
    Data, Knowledge, and Computation
    (KI - Künstliche Intelligenz: Vol. 35, No. 0, 2021) Igel, Christian
  • Zeitschriftenartikel
    Echtzeit-Videoanalyse im Fußball
    (KI - Künstliche Intelligenz: Vol. 27, No. 3, 2013) Schlipsing, Marc; Salmen, Jan; Igel, Christian
    Die Automatisierung der Videoanalyse nimmt im Profisport eine immer wichtigere Rolle ein. Im Fußball kommt dabei der Auswertung der Laufwege der Spieler eine besondere Bedeutung zu. Der vorliegende Bericht dokumentiert unser Kooperationsprojekt zum computergestützten Spieler-Tracking auf Basis von Videobildern in Echtzeit. Wir beschreiben den Aufbau und diskutieren die Praxistauglichkeit des entwickelten Systems, das sich durch hohe Genauigkeit, Mobilität und Kostengünstigkeit auszeichnet.
  • Zeitschriftenartikel
    Editorial
    (KI - Künstliche Intelligenz: Vol. 31, No. 1, 2017) Igel, Christian
  • Zeitschriftenartikel
    Learning ∈ Artificial Intelligence ∩ Cognitive Technologies ∩ Neural Computation ∩ …
    (KI - Künstliche Intelligenz: Vol. 26, No. 3, 2012) Igel, Christian
  • Zeitschriftenartikel
    Remember to Correct the Bias When Using Deep Learning for Regression!
    (KI - Künstliche Intelligenz: Vol. 37, No. 1, 2023) Igel, Christian; Oehmcke, Stefan
    When training deep learning models for least-squares regression, we cannot expect that the training error residuals of the final model, selected after a fixed training time or based on performance on a hold-out data set, sum to zero. This can introduce a systematic error that accumulates if we are interested in the total aggregated performance over many data points (e.g., the sum of the residuals on previously unseen data). We suggest adjusting the bias of the machine learning model after training as a default post-processing step, which efficiently solves the problem. The severeness of the error accumulation and the effectiveness of the bias correction are demonstrated in exemplary experiments.
  • Zeitschriftenartikel
    Remember to Correct the Bias When Using Deep Learning for Regression!
    (KI - Künstliche Intelligenz: Vol. 37, No. 1, 2023) Igel, Christian; Oehmcke, Stefan
    When training deep learning models for least-squares regression, we cannot expect that the training error residuals of the final model, selected after a fixed training time or based on performance on a hold-out data set, sum to zero. This can introduce a systematic error that accumulates if we are interested in the total aggregated performance over many data points (e.g., the sum of the residuals on previously unseen data). We suggest adjusting the bias of the machine learning model after training as a default post-processing step, which efficiently solves the problem. The severeness of the error accumulation and the effectiveness of the bias correction are demonstrated in exemplary experiments.