Fast Learning in Networks of Locally-Tuned Processing Units
The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
We propose a network architecture which uses a single internal layer of locally-tuned processing units to learn both classification tasks and real-valued function approximations (Moody and Darken 1988). We consider training such networks in a completely supervised manner, but abandon this approach in favor of a more computationally efficient hybrid learning method which combines self-organized and supervised learning. Our networks learn faster than backpropagation for two reasons: the local representations ensure that only a few units respond to any given input, thus reducing computational overhead, and the hybrid learning rules are linear rather than nonlinear, thus leading to faster convergence. Unlike many existing methods for data analysis, our network architecture and learning rules are truly adaptive and are thus appropriate for real-time use.
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
(1967) · Cited by 23,719
Least squares quantization in PCM
Lloyd, S. (1982) · IEEE Transactions on Information Theory · doi:10.1109/tit.1982.1056489 · Cited by 15,836
An introduction to computing with neural nets
Lippmann, R. (1987) · IEEE ASSP Magazine · doi:10.1109/massp.1987.1165576 · Cited by 7,825
Networks for approximation and learning
Poggio, T., & Girosi, F. (1990) · Proceedings of the IEEE · doi:10.1109/5.58326 · Cited by 3,252
Predicting chaotic time series
Farmer, J. D., & Sidorowich, J. J. (1987) · Physical Review Letters · doi:10.1103/physrevlett.59.845 · Cited by 1,929
Self-organization and associative memory: 3rd edition
Kohonen, T. (1989) · Springer eBooks · Cited by 1,223
Radial basis functions for multivariable interpolation: a review
Powell, M. J. D. (1987) · Clarendon Press eBooks · Cited by 1,197
Networks and the best approximation property
Girosi, F., & Poggio, T. (1990) · Biological Cybernetics · doi:10.1007/bf00195855 · Cited by 888
Decision theoretic generalizations of the PAC model for neural net and other learning applications
Haussler, D. (1992) · Information and Computation · doi:10.1016/0890-5401(92)90010-d · Cited by 843
Layered Neural Networks with Gaussian Hidden Units as Universal Approximations
Hartman, E. J., Keeler, J. D., & Kowalski, J. M. (1990) · Neural Computation · doi:10.1162/neco.1990.2.2.210 · Cited by 782
Cited by
Items 101–140 of 140
Simplifying fuzzy rule-based models using orthogonal transformation methods
Yen, J., & Wang, L. (1999) · IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) · doi:10.1109/3477.740162 · Cited by 293
(1997) · Elsevier eBooks · doi:10.1016/b978-0-12-526430-3.x5000-4 · Cited by 290
Natural computing for mechanical systems research: A tutorial overview
Worden, K., Staszewski, W. J., & Hensman, J. J. (2011) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2010.07.013 · Cited by 288
Nonparametric multivariate density estimation: a comparative study
Hwang, J.-N., Lay, S.-R., & Lippman, A. (1994) · IEEE Transactions on Signal Processing · doi:10.1109/78.324744 · Cited by 284
Reformulated radial basis neural networks trained by gradient descent
Karayiannis, N. B. (1999) · IEEE Transactions on Neural Networks · doi:10.1109/72.761725 · Cited by 281
Regression modeling in back-propagation and projection pursuit learning
Hwang, J.-N., Lay, S.-R., Maechler, M., Martin, R. D., & Schimert, J. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.286906 · Cited by 278
High-Speed Face Recognition Based on Discrete Cosine Transform and RBF Neural Networks
Er, M. J., Chen, W., & Wu, S. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2005.844909 · Cited by 278
She, C., Wang, Z., Sun, F., Liu, P., & Zhang, L. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2951843 · Cited by 278
On-line EM Algorithm for the Normalized Gaussian Network
Sato, M.-A., & Ishii, S. (2000) · Neural Computation · doi:10.1162/089976600300015853 · Cited by 276
Saravanan, R., & Sujatha, P. (2018) · 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iccons.2018.8663155 · Cited by 269
Similarity Metric Learning for a Variable-Kernel Classifier
Lowe, D. G. (1995) · Neural Computation · doi:10.1162/neco.1995.7.1.72 · Cited by 267
Adaptive fuzzy rule-based classification systems
Nozaki, K., Ishibuchi, H., & Tanaka, H. (1996) · IEEE Transactions on Fuzzy Systems · doi:10.1109/91.531768 · Cited by 267
Simultaneous training of negatively correlated neural networks in an ensemble
Liu, Y., & Yao, X. (1999) · IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) · doi:10.1109/3477.809027 · Cited by 267
A comparative study of different machine learning methods on microarray gene expression data
Pirooznia, M., Yang, J. Y., Yang, M. Q., & Deng, Y. (2008) · BMC Genomics · doi:10.1186/1471-2164-9-s1-s13 · Cited by 259
Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning
Morimoto, J., & Doya, K. (2001) · Robotics and Autonomous Systems · doi:10.1016/s0921-8890(01)00113-0 · Cited by 259
Whitehead, B. A., & Choate, T. D. (1996) · IEEE Transactions on Neural Networks · doi:10.1109/72.508930 · Cited by 253
A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks
Hutchinson, J., Lo, A., & Poggio, T. (1994) · National Bureau of Economic Research · doi:10.3386/w4718 · Cited by 239
Approximation of function and its derivatives using radial basis function networks
Mai-Duy, N., & Tran-Cong, T. (2003) · Applied Mathematical Modelling · doi:10.1016/s0307-904x(02)00101-4 · Cited by 239
Soft computing: the convergence of emerging reasoning technologies
Bonissone, P. P. (1997) · Soft Computing - A Fusion of Foundations, Methodologies and Applications · doi:10.1007/s005000050002 · Cited by 237
“The Feed-Forward networks include single-layer perceptrons, multilayer perceptrons, and Radial Basis function nets (RBFs) see Moody and Darken (1989)], while the Recurrent nets cover Competitive networks, Kohonen (1982) Self Organizing Maps, Hoppeld, J. (1982) nets, and ART models see Carpenter and…”
Data mining techniques for software effort estimation: a comparative study
Dejaeger, K., Verbeke, W., Martens, D., & Baesens, B. (2012) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2011.55 · Cited by 224
Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
Rupp, M., Ramakrishnan, R., & von Lilienfeld, O. A. (2015) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.5b01456 · Cited by 217
Choi, S. W., Park, J. H., & Lee, I.-B. (2004) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2003.09.031 · Cited by 215
Artificial neural networks for computer-based molecular design
Schneider, G., & Wrede, P. (1998) · Progress in Biophysics and Molecular Biology · doi:10.1016/s0079-6107(98)00026-1 · Cited by 213
“Two types of hybrid networks shall brie¯y be mentioned here, radial basis function (RBF) networks (Moody and Darken, 1989; Niranjan and Fallside, 1990) and counter-propagation networks (CPN) (Hecht-Nielsen, 1987, 1988; Huang and Lippmann, 1988).”
BackgroundA parameter optimization method for radial basis function type models
Peng, H., Ozaki, T., Haggan-Ozaki, V., & Toyoda, Y. (2003) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2003.809395 · Cited by 212
“The second approach is first to select the basis function centers by selecting input vectors either algorithmically or at random and setting them to be the centers [4], [9], [10].”
BackgroundOh, B. K., Kim, K. J., Kim, Y., Park, H. S., & Adeli, H. (2017) · Applied Soft Computing · doi:10.1016/j.asoc.2017.05.029 · Cited by 203
Heuristic principles for the design of artificial neural networks
Walczak, S., & Cerpa, N. (1999) · Information and Software Technology · doi:10.1016/s0950-5849(98)00116-5 · Cited by 195
“such as backpropagation (multi-layer perceptron), radial basis function (RBF) [ 35 ],”
BackgroundTraven, H. G. C. (1991) · IEEE Transactions on Neural Networks · doi:10.1109/72.97913 · Cited by 192
Multi-site downscaling of heavy daily precipitation occurrence and amounts
Harpham, C., & Wilby, R. L. (2005) · Journal of Hydrology · doi:10.1016/j.jhydrol.2005.02.020 · Cited by 190
“In this paper, we address this problem via a two-stage modelling procedure using Radial Basis Function (RBF) ANNs (Broomhead and Lowe, 1988; Moody and Darken, 1989) and Multi Layer Perceptron (MLP) ANNs (Rumelhart and McClelland, 1986).”
MethodChen, J., Li, Q., Wang, H., & Deng, M. (2019) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph17010049 · Cited by 189
“The RBF network can approximate any continuous function accurately and is suitable for solving classification problems [34].”
BackgroundGonzalez, J., Rojas, I., Ortega, J., Pomares, H., Fernandez, J., & Diaz, A. (2003) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2003.820657 · Cited by 188
“The optimum values for the weights in can be obtained by solving an overdetermined linear system of equations once the RBFs in have been fixed [5], [57].”
BackgroundMethodDevelopment of Novel Breast Cancer Recurrence Prediction Model Using Support Vector Machine
Kim, W., Kim, K. S., Lee, J. E., Noh, D.-Y., Kim, S.-W., Jung, Y. S., Park, M. Y., & Park, R. W. (2012) · Journal of Breast Cancer · doi:10.4048/jbc.2012.15.2.230 · Cited by 185
“The ANN is a traditional data mining algorithm, and is employed extensively in a variety of clinical areas [25].”
MethodHashemi Fath, A., Madanifar, F., & Abbasi, M. (2020) · Petroleum · doi:10.1016/j.petlm.2018.12.002 · Cited by 178
BACK-PROPAGATION, WEIGHT-ELIMINATION AND TIME SERIES PREDICTION
Weigend, A. S., Rumelhart, D. E., & Huberman, B. A. (1991) · Connectionist Models · doi:10.1016/b978-1-4832-1448-1.50016-0 · Cited by 174
Soft computing system for bank performance prediction
Ravi, V., Kurniawan, H., Thai, P. N. K., & Kumar, P. R. (2008) · Applied Soft Computing · doi:10.1016/j.asoc.2007.02.001 · Cited by 173
“RBFN [31], another member of the feed-forward neural networks, has both unsupervised and supervised training phases.”
BackgroundNiyogi, P., & Girosi, F. (1996) · Neural Computation · doi:10.1162/neco.1996.8.4.819 · Cited by 172
“Second, we explore this relationship in the speci(cid:12)c context of Radial Basis Function networks (Moody and Darken, 1989; Poggio and Girosi, 1990; Powell, 1992).”
MethodData Clustering Using a Model Granular Magnet
Blatt, M., Wiseman, S., & Domany, E. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1805 · Cited by 167
“…data according to natural classes present in it, have been used in a large variety of scientific disciplines and engineering applications that include pattern recognition (Duda and Hart 1973), learning theory (Moody and Darken 1989), astrophysics (Dekel and West 1985), medical image (Suzuki et. al.”
BackgroundNeural Network Forecasting of Tourism Demand
Kon, S. C., & Turner, L. W. (2005) · Tourism Economics · doi:10.5367/000000005774353006 · Cited by 158
“Another model used in time series forecasting is the radial basis function network, or RBF (Broomhead and Lowe, 1989; Moody and Darken, 1989; Leonard et al , 1992; Haykin, 1994).”
MethodNeural Learning from Unbalanced Data
Murphey, Y. L., Guo, H., & Feldkamp, L. A. (2004) · Applied Intelligence · doi:10.1023/b:apin.0000033632.42843.17 · Cited by 82
“A Radial Basis Function (RBF) network has a feedforward architecture that has an internal representation of hidden processing elements that are radially symmetric [7].”
BackgroundField computation in natural and artificial intelligence
MacLennan, B. J. (1999) · Information Sciences · doi:10.1016/s0020-0255(99)00053-5 · Cited by 46
Cheng, J., Xie, B., Lin, C., & Ji, L. (2012) · Bioacoustics · doi:10.1080/09524622.2012.669664 · Cited by 42
Metadata
- Authors
- Moody, J., & Darken, C. J.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- Published
- 1989-06
- Volume
- 1
- Issue
- 2
- Pages
- 281-294
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2171277043
- Cited by
- 4,194
- References
- 20
- FWCI
- 47.84
- 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.