ACL–adaptive correction of learning parameters for backpropagation based algorithms

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschung

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.
OriginalspracheEnglisch
TitelIJCNN '99, International Joint Conference on Neural Networks : Washington, DC, July 10 - 16, 1999, Proceedings
Anzahl der Seiten4
ErscheinungsortPiscataway
VerlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Erscheinungsdatum07.1999
Seiten1749-1752
ISBN (Print)0-7803-5529-6 , 0-7803-5530-X
DOIs
PublikationsstatusErschienen - 07.1999
VeranstaltungInternational Joint Conference on Neural Networks - 1999 - Washington, DC, USA / Vereinigte Staaten
Dauer: 10.07.199916.07.1999
https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6674

DOI

Zuletzt angesehen

Publikationen

  1. Finding Similar Movements in Positional Data Streams
  2. Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images
  3. Evaluating OWL 2 reasoners in the context of checking entity-relationship diagrams during software development
  4. Using trait-based filtering as a predictive framework for conservation
  5. A Multivariate Method for Dynamic System Analysis
  6. A geometric algorithm for the output functional controllability in general manipulation systems and mechanisms
  7. Modified dynamic programming approach for offline segmentation of long hydrometeorological time series
  8. Analysis of Complexity Reduction in Kalman Filters Through Decoupling Control With Chattered Inputs in PMSM
  9. Homogenization modeling of thin-layer-type microstructures
  10. Multi-view learning with dependent views
  11. Machine Learning and Knowledge Discovery in Databases
  12. Comparing the Sensitivity of Social Networks, Web Graphs, and Random Graphs with Respect to Vertex Removal
  13. Reading and Calculating in Word Problem Solving
  14. Using Complexity Metrics to Assess Silent Reading Fluency
  15. Microstructural development of as-cast AM50 during Constrained Friction Processing: grain refinement and influence of process parameters
  16. A coding scheme to analyse global text processing in computer supported collaborative learning: What eye movements can tell us
  17. Classical PI Controllers with Anti-Windup Techniques Applied on Level Systems
  18. A Gait Pattern Generator for Closed-Loop Position Control of a Soft Walking Robot
  19. A two-stage Kalman estimator for motion control using model predictive strategy
  20. Dynamically adjusting the k-values of the ATCS rule in a flexible flow shop scenario with reinforcement learning
  21. Switching Dispatching Rules with Gaussian Processes
  22. Modeling of lateness distributions depending on the sequencing method with respect to productivity effects
  23. Multi-view discriminative sequential learning
  24. Segment Introduction
  25. Parameters Estimation of a Lotka-Volterra Model in an Application for Market Graphics Processing Units
  26. Estimation and interpretation of a Heckman selection model with endogenous covariates
  27. An analytical approach to evaluating bivariate functions of fuzzy numbers with one local extremum
  28. Learning from Erroneous Examples: When and How do Students Benefit from them?
  29. Alternating between Partial and Complete Organization
  30. The fuzzy relationship of intelligence and problem solving in computer simulations
  31. Modeling and simulation of size effects in metallic glasses with non-local continuum mechanics theory
  32. Frame-based Data Factorizations
  33. Representation for interactive exercises
  34. Problem solving in mathematics education
  35. On New Forms of Science Communication and Communication in Science
  36. AGDISTIS-agnostic disambiguation of named entities using linked open data
  37. Interaction-Dominant Causation in Mind and Brain, and Its Implication for Questions of Generalization and Replication
  38. Soil conditions modify species diversity effects on tree functional trait expression