The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Selection of Proper Neural Network Sizes and Architectures—A Comparative Study
Abstract
One of the major difficulties facing researchers using neural networks is the selection of the proper size and topology of the networks. The problem is even more complex because often when the neural network is trained to very small errors, it may not respond properly for patterns not used in the training process. A partial solution proposed to this problem is to use the least possible number of neurons along with a large number of training patterns. The discussion consists of three main parts: first, different learning algorithms, including the Error Back Propagation (EBP) algorithm, the Levenberg Marquardt (LM) algorithm, and the recently developed Neuron-by-Neuron (NBN) algorithm, are discussed and compared based on several benchmark problems; second, the efficiency of different network topologies, including traditional Multilayer Perceptron (MLP) networks, Bridged Multilayer Perceptron (BMLP) networks, and Fully Connected Cascade (FCC) networks, are evaluated by both theoretical analysis and experimental results; third, the generalization issue is discussed to illustrate the importance of choosing the proper size of neural networks.
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
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
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 15,539
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
Orthogonal least squares learning algorithm for radial basis function networks
Chen, S., Cowan, C. F. N., & Grant, P. M. (1991) · IEEE Transactions on Neural Networks · doi:10.1109/72.80341 · Cited by 3,362
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
Cover, T. M. (1965) · IEEE Transactions on Electronic Computers · doi:10.1109/pgec.1965.264137 · Cited by 2,044
Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier]
Arel, I., Rose, D. C., & Karnowski, T. P. (2010) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2010.938364 · Cited by 1,121
An empirical study of learning speed in back-propagation networks
Fahlman, S. E. (2018) · doi:10.1184/r1/6603266 · Cited by 829
State-of-Charge Estimation for Lithium-Ion Batteries Using Neural Networks and EKF
Charkhgard, M., & Farrokhi, M. (2010) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2010.2043035 · Cited by 779
A Generalized Growing and Pruning RBF (GGAP-RBF) Neural Network for Function Approximation
Huang, G.-B., Saratchandran, P., & Sundararajan, N. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.836241 · Cited by 705
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-citationNeural 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
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-citationNeural network architectures and learning algorithms
Wilamowski, B. (2009) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2009.934790 · Cited by 355
Self-citationBhattacharya, A., & Chakraborty, C. (2011) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2010.2070770 · Cited by 335
Deep Machine Learning—A New Frontier in Artificial Intelligence Research
Arel, I., Rose, D. C., & Karnowski, T. P. (2010) · Cited by 314
Backpropagation: past and future
Werbos (1988) · IEEE International Conference on Neural Networks · doi:10.1109/icnn.1988.23866 · Cited by 228
Neural Network Assisted Computationally Simple PI$^\lambda$D$^\mu$ Control of a Quadrotor UAV
Efe, M. Ö. (2011) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2011.2123906 · Cited by 219
Orlowska-Kowalska, T., Dybkowski, M., & Szabat, K. (2010) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2009.2036023 · Cited by 219
Neural Network Learning Without Backpropagation
Wilamowski, B. M., & Yu, H. (2010) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2073482 · Cited by 195
Self-citationNeural MPPT Control of Wind Generators With Induction Machines Without Speed Sensors
Pucci, M., & Cirrincione, M. (2011) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2010.2043043 · Cited by 194
Radial-Basis-Function-Based Neural Network for Harmonic Detection
Chang, G. W., Chen, C.-I., & Teng, Y.-F. (2010) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2009.2034681 · Cited by 189
Comparison between traditional neural networks and radial basis function networks
Xie, T., Yu, H., & Wilamowski, B. M. (2011) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie.2011.5984328 · Cited by 176
Self-citationMultilayer Perceptrons: Approximation Order and Necessary Number of Hidden Units
Trenn, S. (2008) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2007.912306 · Cited by 173
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-citationOrłowska-Kowalska, T., & Kamiński, M. (2011) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2011.2158843 · Cited by 155
Wavelet Fuzzy Neural Networks for Identification and Predictive Control of Dynamic Systems
Lu, C. (2010) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2010.2076415 · Cited by 153
Cascade Neural-Network-Based Fault Classifier for Three-Phase Induction Motor
Ghate, V. N., & Dudul, S. V. (2010) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2010.2053337 · Cited by 149
Gomperts, A., Ukil, A., & Zurfluh, F. (2010) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2010.2085006 · Cited by 145
El-Sousy, F. F. M. (2010) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2009.2038331 · Cited by 138
Learning Speaker-Specific Characteristics With a Deep Neural Architecture
Chen, K., & Salman, A. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2011.2167240 · Cited by 113
Oil well diagnosis by sensing terminal characteristics of the induction motor
Wilamowski, B. M., & Kaynak, O. (2000) · IEEE Transactions on Industrial Electronics · doi:10.1109/41.873219 · Cited by 83
Self-citationParameter Incremental Learning Algorithm for Neural Networks
Wan, S. H., & Banta, L. E. (2006) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2006.880581 · Cited by 77
Solving 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-citationRobust Neural Network Tracking Controller Using Simultaneous Perturbation Stochastic Approximation
Song, Q., Spall, J. C., Soh, Y. C., & Ni, J. (2008) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2007.912315 · Cited by 62
A Constrained Optimization Approach to Preserving Prior Knowledge During Incremental Training
Ferrari, S., & Jensenius, M. A. (2008) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2007.915108 · Cited by 51
Juang, C., Chang, Y., & Hsiao, C.-M. (2010) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2010.2072892 · Cited by 49
Challenges in applications of computational intelligence in industrial electronics
Wilamowski, B. M. (2010) · IEEE International Symposium on Industrial Electronics (ISIE) · doi:10.1109/isie.2010.5637934 · Cited by 38
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-citationInjecting Knowledge into the Solution of the Two-Spiral Problem
Álvarez, J. R. (1999) · Neural Computing and Applications · doi:10.1007/s005210050029 · Cited by 30
Cited by
The internet of things: a survey
Li, S., Xu, L. D., & Zhao, S. (2015) · Information Systems Frontiers · doi:10.1007/s10796-014-9492-7 · Cited by 2,297
Review on Methods to Fix Number of Hidden Neurons in Neural Networks
Sheela, K. G., & Deepa, S. N. (2013) · Mathematical Problems in Engineering · doi:10.1155/2013/425740 · Cited by 941
Khayyam, H., Jazar, R. N., Nunna, S., Golkarnarenji, G., Badii, K., Fakhrhoseini, S. M., Kumar, S., & Naebe, M. (2020) · Progress in Materials Science · doi:10.1016/j.pmatsci.2019.100575 · Cited by 325
Deshpande, G., Wang, P., Rangaprakash, D., & Wilamowski, B. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2379621 · Cited by 161
Self-citation
Metadata
- Authors
- Hunter, D., Yu, H., Pukish, III, Kolbusz, J., & Wilamowski, B. M.
- Venue
- IEEE Transactions on Industrial Informatics
- Published
- 2012-05
- Volume
- 8
- Issue
- 2
- Pages
- 228-240
- ISSN
- 1551-3203 (ISSN-L)
- 1941-0050
- OpenAlex
- W2125818553
- Cited by
- 415
- References
- 42
- FWCI
- 23.75
- 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.