Convolutional Neural Networks

Research output: Contributions to collected editions/worksChapter

Authors

Dieses Kapitel führt in Convolutional Neural Networks (CNNs) ein und beschreibt, wie diese im Kontext der Sportanalyse verwendet werden können. Insbesondere eignen sich CNNs für das End-to-End-Lernen auf Bildern oder ähnlich strukturierten Daten. Dabei können CNNs Merkmale von Bildern anhand der Pixelwerte effizient lernen und beispielsweise sehr gute Merkmale für eine Klassifikationsaufgabe extrahieren. Die Modelle profitieren dabei von Parameter Sharing in den Convolutional Layern und zeichnen sich durch (bedingte) Translationsäquivarianz und -invarianz aus. CNNs eignen sich auch dafür, Merkmale aus Positionsdaten von Teamsportarten zu lernen, sofern die Daten in eine entsprechende Struktur gebracht werden.
Original languageEnglish
Title of host publicationSportinformatik : Modellbildung, Simulation, Datenanalyse und Visualisierung von sportbezogenen Daten
EditorsDaniel Memmert
Number of pages9
Place of PublicationBerlin
PublisherSpringer Spektrum
Publication date01.01.2023
Pages207-215
ISBN (print)978-3-662-67025-5
ISBN (electronic)978-3-662-67026-2
DOIs
Publication statusPublished - 01.01.2023

Bibliographical note

© Der/die Autor(en), exklusiv lizenziert an Springer-Verlag GmbH, DE, ein Teil von Springer Nature 2023

Recently viewed

Publications

  1. Situated multiplying in primary school
  2. Topic Embeddings – A New Approach to Classify Very Short Documents Based on Predefined Topics
  3. Concept for Process Parameter-Based Inline Quality Control as a Basis for Pairing in a Production Line
  4. Control of a Three-Axis Robot with Super Twisting Sliding Mode Control
  5. Informatik
  6. Reading and Calculating in Word Problem Solving
  7. A New Framework for Production Planning and Control to Support the Positioning in Fields of Tension Created by Opposing Logistic Objectives
  8. Cognitive load and instructionally supported learning with provided and learner-generated visualizations
  9. Grazing, exploring and networking for sustainability-oriented innovations in learning-action networks
  10. Using Local and Global Self-Evaluations to Predict Students' Problem Solving Behaviour
  11. Using heuristic worked examples to promote solving of reality‑based tasks in mathematics in lower secondary school
  12. Errors, error taxonomies, error prevention, and error management
  13. Integrating the underlying structure of stochasticity into community ecology
  14. A tutorial introduction to adaptive fractal analysis
  15. Special Issue in Acquisitional Pragmatics in Foreign Language Learning
  16. Human–learning–machines: introduction to a special section on how cybernetics and constructivism inspired new forms of learning
  17. Mathematics in Robot Control for Theoretical and Applied Problems
  18. Using Complexity Metrics to Assess Silent Reading Fluency
  19. Globally asymptotic output feedback tracking of robot manipulators with actuator constraints
  20. Multilevel bridge governor by using model predictive control in wavelet packets for tracking trajectories
  21. Latent structure perceptron with feature induction for unrestricted coreference resolution
  22. Challenges and boundaries in implementing social return on investment
  23. XOperator - Interconnecting the semantic web and instant messaging networks
  24. Challenges in detecting proximal effects of existential threat on lie detection accuracy
  25. Experiments on the Fehrer-Raab effect and the ‘Weather Station Model’ of visual backward masking
  26. Parking space management through deep learning – an approach for automated, low-cost and scalable real-time detection of parking space occupancy
  27. Assembly Theory for Restoring Ecosystem Structure and Functioning
  28. Constructions and Reconstructions. The Architectural Image between Rendering and Photography
  29. Lyapunov stability analysis to set up a PI controller for a mass flow system in case of a non-saturating input