The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Neural network architectures and learning algorithms
Abstract
Neural networks are the topic of this paper. Neural networks are very powerful as nonlinear signal processors, but obtained results are often far from satisfactory. The purpose of this article is to evaluate the reasons for these frustrations and show how to make these neural networks successful. The following are the main challenges of neural network applications: (1) Which neural network architectures should be used? (2) How large should a neural network be? (3) Which learning algorithms are most suitable? The multilayer perceptron (MLP) architecture is unfortunately the preferred neural network topology of most researchers. It is the oldest neural network architecture, and it is compatible with all training softwares. However, the MLP topology is less powerful than other topologies such as bridged multilayer perceptron (BMLP), where connections across layers are allowed. The error-back propagation (EBP) algorithm is the most popular learning algorithm, but it is very slow and seldom gives adequate results. The EBP training process requires 100-1,000 times more iterations than the more advanced algorithms such as Levenberg-Marquardt (LM) or neuron by neuron (NBN) algorithms. What is most important is that the EBP algorithm is not only slow but often it is not able to find solutions for close-to-optimum neural networks. The paper describes and compares several learning algorithms.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Fuzzy identification of systems and its applications to modeling and control
Takagi, T., & Sugeno, M. (1985) · IEEE Transactions on Systems, Man, and Cybernetics · doi:10.1109/tsmc.1985.6313399 · Cited by 19,592
A method for the solution of certain non-linear problems in least squares
Levenberg, K. (1944) · Quarterly of Applied Mathematics · doi:10.1090/qam/10666 · Cited by 12,359
Training feedforward networks with the Marquardt algorithm
Hagan, M. T., & Menhaj, M. B. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.329697 · Cited by 7,701
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
Riedmiller, M., & Braun, H. (2002) · IEEE International Conference on Neural Networks · doi:10.1109/icnn.1993.298623 · Cited by 3,917
Advances in Neural Information Processing Systems 37
(2024) · doi:10.52202/079017 · Cited by 2,791
Structure identification of fuzzy model
Sugeno, M., & Kang, G. T. (1988) · Fuzzy Sets and Systems · doi:10.1016/0165-0114(88)90113-3 · Cited by 2,715
The Cascade-Correlation learning architecture
Fahlman, S. E., & Lebiere, C. J. (2018) · doi:10.1184/r1/6610403 · Cited by 2,372
Fast-learning variations on back propagation: an empirical study.
Fahlman, S. E. (1989) · Medical Entomology and Zoology · Cited by 725
Neural Network Applications in Power Electronics and Motor Drives—An Introduction and Perspective
Bose, B. K. (2007) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2006.888683 · Cited by 520
Computing Gradient Vector and Jacobian Matrix in Arbitrarily Connected Neural Networks
Wilamowski, B. M., Cotton, N. J., Kaynak, O., & Dündar, G. (2008) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2008.2003319 · Cited by 155
Self-citationSolving parity-N problems with feedforward neural networks
Wilamowski, B. M., Hunter, D., & Mabnowski, A. (2004) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2003.1223966 · Cited by 67
Self-citationEfficient and reliable training of neural networks
Yu, H., & Wilamowski, B. M. (2009) · Conference on Human System Interactions · doi:10.1109/hsi.2009.5090963 · Cited by 35
Self-citationNeural Networks and Fuzzy Systems for Nonlinear Applications
Wilamowski, B. M. (2007) · IEEE International Conference on Intelligent Engineering Systems (INES) · doi:10.1109/ines.2007.4283665 · Cited by 22
Self-citationSpecial neural network architectures for easy electronic implementations
Wilamowski, B. M. (2009) · International Conference on Power Engineering, Energy and Electrical Drives · doi:10.1109/powereng.2009.4915141 · Cited by 9
Self-citation
Cited by
Improved Computation for Levenberg–Marquardt Training
Wilamowski, B. M., & Yu, H. (2010) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2045657 · Cited by 622
Self-citationOptimal Energy Storage Sizing and Control for Wind Power Applications
Brekken, T. K. A., Yokochi, A., von Jouanne, A., Yen, Z. Z., Hapke, H. M., & Halamay, D. A. (2010) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2010.2066294 · Cited by 501
Advantages of Radial Basis Function Networks for Dynamic System Design
Yu, H., Xie, T., Paszczynski, S., & Wilamowski, B. M. (2011) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2011.2164773 · Cited by 445
Self-citationSelection of Proper Neural Network Sizes and Architectures—A Comparative Study
Hunter, D., Yu, H., Pukish, III, Kolbusz, J., & Wilamowski, B. M. (2012) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2012.2187914 · Cited by 415
Self-citationYu, H., & Wilamowski, B. (2011) · Electrical Engineering Handbook · doi:10.1201/b10604-15 · Cited by 395
Self-citation
Metadata
- Authors
- Wilamowski, B.
- Venue
- IEEE Industrial Electronics Magazine
- Published
- 2009-12
- Volume
- 3
- Issue
- 4
- Pages
- 56-63
- ISSN
- 1932-4529 (ISSN-L)
- OpenAlex
- W2019282798
- Cited by
- 355
- References
- 16
- FWCI
- 27.11
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.