The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions
Abstract
It is well known that standard single-hidden layer feedforward networks (SLFNs) with at most N hidden neurons (including biases) can learn N distinct samples (x(i),t(i)) with zero error, and the weights connecting the input neurons and the hidden neurons can be chosen "almost" arbitrarily. However, these results have been obtained for the case when the activation function for the hidden neurons is the signum function. This paper rigorously proves that standard single-hidden layer feedforward networks (SLFNs) with at most N hidden neurons and with any bounded nonlinear activation function which has a limit at one infinity can learn N distinct samples (x(i),t(i)) with zero error. The previous method of arbitrarily choosing weights is not feasible for any SLFN. The proof of our result is constructive and thus gives a method to directly find the weights of the standard SLFNs with any such bounded nonlinear activation function as opposed to iterative training algorithms in the literature.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,081
Approximation capabilities of multilayer feedforward networks
Hornik, K. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90009-t · Cited by 6,091
On the approximate realization of continuous mappings by neural networks
Funahashi, K.-I. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90003-8 · Cited by 4,206
Leshno, M., Lin, V. Y., Pinkus, A., & Schocken, S. (1993) · Neural Networks · doi:10.1016/s0893-6080(05)80131-5 · Cited by 2,121
Chen, T., & Chen, H. (1995) · IEEE Transactions on Neural Networks · doi:10.1109/72.392253 · Cited by 1,230
Networks and the best approximation property
Girosi, F., & Poggio, T. (1990) · Biological Cybernetics · doi:10.1007/bf00195855 · Cited by 888
Kolmogorov's theorem and multilayer neural networks
Kůrková, V. (1992) · Neural Networks · doi:10.1016/0893-6080(92)90012-8 · Cited by 747
A Theory of Networks for Approximation and Learning
Poggio, T., & Girosi, F. (1989) · Cited by 703
Chen, T., & Chen, H. (1995) · IEEE Transactions on Neural Networks · doi:10.1109/72.392252 · Cited by 394
On the capabilities of multilayer perceptrons
Baum, E. B. (1988) · Journal of Complexity · doi:10.1016/0885-064x(88)90020-9 · Cited by 379
Bounds on the number of hidden neurons in multilayer perceptrons
Huang, S.-C., & Huang, Y.-F. (1991) · IEEE Transactions on Neural Networks · doi:10.1109/72.80290 · Cited by 328
Stinchcombe, & White (1989) · International Joint Conference on Neural Networks · doi:10.1109/ijcnn.1989.118640 · Cited by 251
There exists a neural network that does not make avoidable mistakes
Gallant, & White (1988) · IEEE International Conference on Neural Networks · doi:10.1109/icnn.1988.23903 · Cited by 205
A simple method to derive bounds on the size and to train multilayer neural networks
Sartori, M. A., & Antsaklis, P. J. (1991) · IEEE Transactions on Neural Networks · doi:10.1109/72.88168 · Cited by 182
Approximation capability in C(R~/sup n/) by multilayer feedforward networks and related problems
Chen, T., Chen, H., & Liu, R.-W. (1995) · IEEE Transactions on Neural Networks · doi:10.1109/72.363453 · Cited by 176
Arbitrary nonlinearity is sufficient to represent all functions by neural networks: A theorem
Крейнович, В. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90074-f · Cited by 145
Ito, Y. (1992) · Neural Networks · doi:10.1016/s0893-6080(05)80009-7 · Cited by 122
Approximation of functions on a compact set by finite sums of a sigmoid function without scaling
Ito, Y. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90060-i · Cited by 117
Neural networks, approximation theory, and finite precision computation
Wray, J., & Green, G. G. R. (1995) · Neural Networks · doi:10.1016/0893-6080(94)00056-r · Cited by 76
Constructive neural networks with piecewise interpolation capabilities for function approximations
Choi, C., & Choi, J. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.329691 · Cited by 37
Cited by
Extreme learning machine: Theory and applications
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006) · Neurocomputing · doi:10.1016/j.neucom.2005.12.126 · Cited by 13,285
Self-citationExtreme learning machine: a new learning scheme of feedforward neural networks
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2005) · 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541) · doi:10.1109/ijcnn.2004.1380068 · Cited by 4,084
Self-citationUniversal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes
Huang, G.-B., Chen, L., & Siew, C.-K. (2006) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2006.875977 · Cited by 2,614
Self-citationA Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks
Liang, N.-Y., Huang, G.-B., Saratchandran, P., & Sundararajan, N. (2006) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2006.880583 · Cited by 1,965
Self-citationExtreme learning machines: a survey
Huang, G.-B., Wang, D. H., & Lan, Y. (2011) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-011-0019-y · Cited by 1,914
Self-citation
Metadata
- Authors
- Huang, G.-B., & Babri, H. A.
- Venue
- IEEE Transactions on Neural Networks
- Published
- 1998
- Volume
- 9
- Issue
- 1
- Pages
- 224-229
- ISSN
- 1045-9227 (ISSN-L)
- OpenAlex
- W2167982865
- Cited by
- 538
- References
- 22
- FWCI
- 1.31
- 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.