ACL–adaptive correction of learning parameters for backpropagation based algorithms

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearch

Standard

ACL–adaptive correction of learning parameters for backpropagation based algorithms. / Wilk, Jan; Wilk, Eva; Gobel, H.
IJCNN '99, International Joint Conference on Neural Networks: Washington, DC, July 10 - 16, 1999, Proceedings. Piscataway: IEEE - Institute of Electrical and Electronics Engineers Inc., 1999. p. 1749-1752 (International Joint Conference on Neural Networks. Proceedings; Vol. 3).

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearch

Harvard

Wilk, J, Wilk, E & Gobel, H 1999, ACL–adaptive correction of learning parameters for backpropagation based algorithms. in IJCNN '99, International Joint Conference on Neural Networks: Washington, DC, July 10 - 16, 1999, Proceedings. International Joint Conference on Neural Networks. Proceedings, vol. 3, IEEE - Institute of Electrical and Electronics Engineers Inc., Piscataway, pp. 1749-1752, International Joint Conference on Neural Networks - 1999, Washington, DC, Washington, United States, 10.07.99. https://doi.org/10.1109/IJCNN.1999.832641

APA

Wilk, J., Wilk, E., & Gobel, H. (1999). ACL–adaptive correction of learning parameters for backpropagation based algorithms. In IJCNN '99, International Joint Conference on Neural Networks: Washington, DC, July 10 - 16, 1999, Proceedings (pp. 1749-1752). (International Joint Conference on Neural Networks. Proceedings; Vol. 3). IEEE - Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.1999.832641

Vancouver

Wilk J, Wilk E, Gobel H. ACL–adaptive correction of learning parameters for backpropagation based algorithms. In IJCNN '99, International Joint Conference on Neural Networks: Washington, DC, July 10 - 16, 1999, Proceedings. Piscataway: IEEE - Institute of Electrical and Electronics Engineers Inc. 1999. p. 1749-1752. (International Joint Conference on Neural Networks. Proceedings). doi: 10.1109/IJCNN.1999.832641

Bibtex

@inbook{1a357b8f5e3b401a9b2054dabf3190ed,
title = "ACL–adaptive correction of learning parameters for backpropagation based algorithms",
abstract = "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.",
keywords = "Informatics",
author = "Jan Wilk and Eva Wilk and H. Gobel",
year = "1999",
month = jul,
doi = "10.1109/IJCNN.1999.832641",
language = "English",
isbn = "0-7803-5529-6 ",
series = "International Joint Conference on Neural Networks. Proceedings",
publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",
pages = "1749--1752",
booktitle = "IJCNN '99, International Joint Conference on Neural Networks",
address = "United States",
note = "International Joint Conference on Neural Networks - 1999, IJCNN '99 ; Conference date: 10-07-1999 Through 16-07-1999",
url = "https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6674",

}

RIS

TY - CHAP

T1 - ACL–adaptive correction of learning parameters for backpropagation based algorithms

AU - Wilk, Jan

AU - Wilk, Eva

AU - Gobel, H.

PY - 1999/7

Y1 - 1999/7

N2 - 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.

AB - 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.

KW - Informatics

U2 - 10.1109/IJCNN.1999.832641

DO - 10.1109/IJCNN.1999.832641

M3 - Article in conference proceedings

SN - 0-7803-5529-6

SN - 0-7803-5530-X

T3 - International Joint Conference on Neural Networks. Proceedings

SP - 1749

EP - 1752

BT - IJCNN '99, International Joint Conference on Neural Networks

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

CY - Piscataway

T2 - International Joint Conference on Neural Networks - 1999

Y2 - 10 July 1999 through 16 July 1999

ER -

Recently viewed

Publications

  1. Neural network-based adaptive fault-tolerant control for strict-feedback nonlinear systems with input dead zone and saturation
  2. Database enhanced acceleration method based on multivariate simplicial interpolation for material-dominated calculations
  3. Algebraic combinatorics in mathematical chemistry. Methods and algorithms. I. Permutation groups and coherent (cellular) algebras.
  4. Set-oriented numerical computation of rotation sets
  5. Learning Rotation Sensitive Neural Network for Deformed Objects' Detection in Fisheye Images
  6. Selecting and Adapting Methods for Analysis and Design in Value-Sensitive Digital Social Innovation Projects: Toward Design Principles
  7. Invariant subspaces for grasping internal forces and non-interacting force-motion control in robotic manipulation
  8. Classical PI Controllers with Anti-Windup Techniques Applied on Level Systems
  9. Lagged Multidimensional Recurrence Quantification Analysis for Determining Leader–Follower Relationships Within Multidimensional Time Series
  10. Effective informational entropy reduction in multi-robot systems based on real-time TVS
  11. Positioning Improvement for a Laser Scanning System using cSORPD control
  12. Improved sensorimotor control is not connected with improved proprioception
  13. Machine Learning and Knowledge Discovery in Databases
  14. Competing Vegetation Structure Indices for Estimating Spatial Constrains in Carabid Abundance Patterns in Chinese Grasslands Reveal Complex Scale and Habitat Patterns
  15. Advances in Dynamics, Optimization and Computation
  16. Does thinking-aloud affect learning, visual information processing and cognitive load when learning with seductive details as expected from self-regulation perspective?
  17. Cognitive load and instructionally supported learning with provided and learner-generated visualizations
  18. Resource extraction technologies - is a more responsible path of development possible?
  19. Using augmented video to test in-car user experiences of context analog HUDs
  20. Robust Control of Mobile Transportation Object with 3D Technical Vision System
  21. How Much Home Office is Ideal? A Multi-Perspective Algorithm
  22. Efficient Order Picking Methods in Robotic Mobile Fulfillment Systems
  23. Guided discovery learning with computer-based simulation games
  24. Probabilistic approach to modelling of recession curves
  25. Eighth Workshop on Mining and Learning with Graphs
  26. Mostly harmless econometrics? Statistical paradigms in the ‘top five’ from 2000 to 2018
  27. Learning and Re-learning from net- based cooperative learning discourses
  28. Using Heider’s Epistemology of Thing and Medium for Unpacking the Conception of Documents: Gantt Charts and Boundary Objects
  29. Topic Embeddings – A New Approach to Classify Very Short Documents Based on Predefined Topics
  30. Transfer operator-based extraction of coherent features on surfaces
  31. Optimising business performance with standard software systems
  32. Reality-Based Tasks with Complex-Situations
  33. On the Difficulty of Forgetting
  34. An experience-based learning framework