Comparison of Backpropagation and Kalman Filter-based Training for Neural Networks

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

This work describes and compares the backpropagation algorithm with the extended Kalman filter (EKF), a second-order training method which can be applied to the problem of learning neural network parameters and is known to converge in only a few iterations. The algorithms are compared with respect to their effectiveness and speed of convergence using simulated data for both, a regression and a classification task.

Original languageEnglish
Title of host publication2021 25th International Conference on System Theory, Control and Computing (ICSTCC) : October 20 – 23, 2021 Iași, ROMANIA, Proceedings
EditorsLavinia Ferariu, Mihaela-Hanako Matcovschi, Florina Ungureanu
Number of pages8
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers Inc.
Publication date20.10.2021
Pages234-241
ISBN (print)978-1-6654-3055-5
ISBN (electronic)978-1-6654-1496-8
DOIs
Publication statusPublished - 20.10.2021
Event25th International Conference on System Theory, Control and Computing - Iasi, Romania
Duration: 20.10.202123.10.2021
Conference number: 25
https://ieeexplore.ieee.org/xpl/conhome/9607028/proceeding

    Research areas

  • Backpropagation Algorithm, Kalman Filter, Neural Networks
  • Engineering

Recently viewed

Researchers

  1. Thomas Gann

Publications

  1. Creative spaces in computer science
  2. Introduction to the challenges and chances regarding the utilization of nitrogen-rich by-products and waste streams
  3. Learning in the "Third Space"
  4. Process Analysis of Grounding Activities in Net-Based Cooperative Learning
  5. Unraveling Privacy Concerns in Complex Data Ecosystems with Architectural Thinking
  6. Which nudges get support - A Quantitative Analysis of the Dimensions Transparency and Dual Process Theory
  7. Integrating inductive and deductive analysis to identify and characterize archetypical social-ecological systems and their changes
  8. Some surprising differences between novice and expert errors in computerized office work
  9. Error handling in office work with computers
  10. Low working memory reduces the use of mental contrasting
  11. Accuracy, latency, and confidence in abstract reasoning: The influence of fear of failure and gender
  12. Estimated substitution elasticities of a nested CES production function approach for Germany
  13. Analysis of the relevance of models, influencing factors and the point in time of the forecast on the prediction quality in order-related delivery time determination using machine learning
  14. Are Acute Effects of Foam-Rolling Attributed to Dynamic Warm Up Effects? A Comparative Study
  15. Application of friction surfacing for solid state additive manufacturing of cylindrical shell structures
  16. Modeling a modular omnidirectional AGV developmental platform with integrated suspension and power-plant
  17. TANGO: A reliable, open-source, browser-based task to assess individual differences in gaze understanding in 3 to 5-year-old children and adults
  18. Evaluation of a Four-Week Online Resilience Training Program for Multiple Sclerosis Patients
  19. "Die Arbeit funktioniert"
  20. Identification of Parameters and States in PMSMs
  21. Complexity of traffic scenes and EEG-measures of processing workload in car driving
  22. Grounding Space
  23. U-model-based dynamic inversion control for quadrotor UAV systems
  24. Stimulus complexity determined by fractal geometry
  25. Introduction to Automatic Imitation
  26. From Fleeting Enchantment to Embodied Commitment