1. //
  2. Start
  3. //
  4. Publications
  5. //
  6. ACL–adaptive correction of learning para...
  7. //

ACL–adaptive correction of learning parameters for backpropagation based algorithms

Research output: Contributions to collected editions/works › Article in conference proceedings › Research

Authors

We present an improvement of backpropagation learning (BP) for Sigma-Pi networks with adaptive correction of the learning parameters (ACL). An improvement of convergency is achieved by using the information value, change of the output error and the validity of Funahashi's theorem to analytically determine values for the learning parameters momentum, learning rate and learning motivation in each learning step. Its application to a neural-network based approximation of continuous input-output mappings with high accuracy yields very good results: the number of training periods of ACL BP learning is smaller than the corresponding number of training periods using other BP based learning rules.
Original languageEnglish
Title of host publicationIJCNN '99, International Joint Conference on Neural Networks : Washington, DC, July 10 - 16, 1999, Proceedings
Number of pages4
Place of PublicationPiscataway
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date07.1999
Pages1749-1752
ISBN (print)0-7803-5529-6 , 0-7803-5530-X
DOIs
Publication statusPublished - 07.1999
EventInternational Joint Conference on Neural Networks - 1999 - Washington, DC, United States
Duration: 10.07.1999 → 16.07.1999
https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6674

Other publications by the same author(s)

A control strategy for electromagnetic near and far field calculation

Wilk, J. & Röhm, H., 05.09.2001, ICECS 2001 - 8th IEEE International Conference on Electronics, Circuits and Systems: The 8th IEEE International Conference On Electronics, Circuits and Systems . IEEE - Institute of Electrical and Electronics Engineers Inc., Vol. 3. p. 1327-1330 4 p. 957458. (Proceedings of the IEEE International Conference on Electronics, Circuits, and Systems; vol. 3).

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

Optimized neural networks for modeling of loudspeaker directivity diagrams

Wilk, E. & Wilk, J., 05.2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing : Proceedings. IEEE - Institute of Electrical and Electronics Engineers Inc., Vol. 2. p. 1285-1288 4 p. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Contributions to collected editions/works › Article in conference proceedings › Research

DOI

Recently viewed

Activities

  1. Digital Control of a Camless Engine Using Lyapunov Approach with Backward Euler Approximation
  2. Set-oriented computation in dynamics
  3. Contributions of declarative and procedural memory to second language accuracy and automatization
  4. Modeling Efficient Grounding in Chat-based CSCL: An Approach for Adaptive Scripting?
  5. HyperImage: Image-Oriented e-Science Networks
  6. Comparing Two Voltage Observers in a Sensorsystem using Repetitive Control
  7. Principal Ambidexterity: Exploring and Exploiting in dynamic Contexts
  8. Computer Simulations in Design. How Social Media meet Computational Methods in Design Processes
  9. Probabilistic and discrete methods for the computational study of coherent behavior in flows
  10. Interpreting Strings, Weaving Threads – Structuring Provenance Data with AI
  11. Small Input Devices Used by the Elderly – How Sensorimotor Transformation and Task Complexity Affect Interaction
  12. Learner Performance of Language Learning Tasks in Web-Based Environments
  13. Probabilistic and discrete methods for the computational study of coherent behavior in flows
  14. Multi-Agent Path Finding with Kinematic Constraints for Robotic Mobile Fulfillment Systems
  15. Graph Conditional Variational Models: Too Complex for Multiagent Trajectories?
  16. Applications of transfer operator methods in fluid dynamics
  17. Exploiting the Frame for Active Learning in Multi-class Classification
  18. Model Predictive Control for Switching Gain Adaptation in a Sliding Mode Controller of a DC Drive with Nonlinear Friction

Publications

  1. Fostering Circularity: Building a Local Community and Implementing Circular Processes
  2. Advanced Neural Classifier-Based Effective Human Assistance Robots Using Comparable Interactive Input Assessment Technique
  3. Calculation of Average Mutual Information (AMI) and false-nearest neighbors (FNN) for the estimation of embedding parameters of multidimensional time series in matlab
  4. Database enhanced acceleration method based on multivariate simplicial interpolation for material-dominated calculations
  5. Using trait-based filtering as a predictive framework for conservation
  6. A rough-and-ready cluster-based approach for extracting finite-time coherent sets from sparse and incomplete trajectory data
  7. Wavelet based Fault Detection and RLS Parameter Estimation of Conductive Fibers with a Simultaneous Estimation of Time-Varying Disturbance
  8. Preventive Emergency Detection Based on the Probabilistic Evaluation of Distributed, Embedded Sensor Networks
  9. Design of a Real Time Path of Motion Using a Sliding Mode Control with a Switching Surface
  10. A two-step approach for the prediction of mood levels based on diary data
  11. Setting controller parameters through a minimum strategy with a weighted least squares method
  12. Dynamic adjustment of dispatching rule parameters in flow shops with sequence-dependent set-up times
  13. Learning with animations and simulations in a computer-based learning environment about torques
  14. Modeling and simulation of inelastic microstructure development and inhomogeneous material behavior via non-convex rate dependent gradient plasticity
  15. Heuristic approximation and computational algorithms for closed networks
  16. Graph Conditional Variational Models: Too Complex for Multiagent Trajectories?
  17. Supervised clustering of streaming data for email batch detection
  18. Development of a Didactic Graphical Simulation Interface on MATLAB for Systems Control
  19. A development approach for a standardized quality data model using asset administration shell technology in the context of autonomous quality control loops for manufacturing processes
  20. Evolutionary generation of dispatching rule sets for complex dynamic scheduling problems
  21. Set-oriented numerical computation of rotation sets
  22. Linear Generalised Model Predictive Control to Avoid Input Saturation through Matrix Conditions
  23. Using Natural Language Processing Techniques to Tackle the Construct Identity Problem in Information Systems Research
  24. A genetic algorithm for a self-learning parameterization of an aerodynamic part feeding system for high-speed assembly
  25. Using Euler Discrete Approximation to Control an Aggregate Actuator in Camless Engines
  26. Database Publishing Without Databases
  27. Insights from classifying visual concepts with multiple kernel learning
  28. Semi-supervised learning for structured output variables
  29. Global text processing in CSCL with learning protocols
  30. Detection and mapping of water pollution variation in the Nile Delta using multivariate clustering and GIS techniques