Classification ability of single hidden layer feedforward neural networks

Authors:
Guang-Bin Huang;Yan-Qiu Chen;H. A. Babri
Affiliations:
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ.;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
2000

Citing 0
Cited 24

Performance Evaluation of GAP-RBF Network in Channel Equalization

Neural Processing Letters
Flank wear prediction in drilling using back propagation neural network and radial basis function network

Applied Soft Computing
Neural network structures with constant weights to implement dis-jointly removed non-convex (DJRNC) decision regions: part a - properties, model, and simple case

NN'07 Proceedings of the 8th Conference on 8th WSEAS International Conference on Neural Networks - Volume 8
A neural network structure with constant weights to implement convex recursive deletion regions

NN'07 Proceedings of the 8th Conference on 8th WSEAS International Conference on Neural Networks - Volume 8
An error-counting network for pattern classification

Neurocomputing
On implementation of nested rectangular decision regions by multi-layer perceptrons I: algorithm

NN'06 Proceedings of the 7th WSEAS International Conference on Neural Networks
On implementation of nested rectangular decision regions by multi-layer perceptrons II: properties and feasibility

NN'06 Proceedings of the 7th WSEAS International Conference on Neural Networks
Deterministic neural classification

Neural Computation
A Robust Online Sequential Extreme Learning Machine

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Implementation feasibility of convex recursive deletion regions using multi-layer perceptrons

WSEAS Transactions on Computers
Neural network based detection of hard exudates in retinal images

Computer Methods and Programs in Biomedicine
Small Number of Hidden Units for ELM with Two-Stage Linear Model

IEICE - Transactions on Information and Systems
Multi step ahead prediction of north and south hemisphere sun spots chaotic time series using focused time lagged recurrent neural network model

WSEAS Transactions on Information Science and Applications
Letters: Fully complex extreme learning machine

Neurocomputing
Classification methodologies of multilayer perceptrons with sigmoid activation functions

Pattern Recognition
Classification of material type and its surface properties using digital signal processing techniques and neural networks

Applied Soft Computing
Two-stage extreme learning machine for regression

Neurocomputing
Novel FTLRNN with gamma memory for short-term and long-term predictions of chaotic time series

Applied Computational Intelligence and Soft Computing
Channel equalization using complex extreme learning machine with RBF kernels

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part III
Recursive complex extreme learning machine with widely linear processing for nonlinear channel equalizer

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part III
A quantitative comparison of different MLP activation functions in classification

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Neural network generalized inverse of multi-motor synchronous system working on vector control mode

ICIC'11 Proceedings of the 7th international conference on Intelligent Computing: bio-inspired computing and applications
Combining sclera and periocular features for multi-modal identity verification

Neurocomputing
Time-series processing of large scale remote sensing data with extreme learning machine

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multilayer perceptrons with hard-limiting (signum) activation functions can form complex decision regions. It is well known that a three-layer perceptron (two hidden layers) can form arbitrary disjoint decision regions and a two-layer perceptron (one hidden layer) can form single convex decision regions. This paper further proves that single hidden layer feedforward neural networks (SLFN) with any continuous bounded nonconstant activation function or any arbitrary bounded (continuous or not continuous) activation function which has unequal limits at infinities (not just perceptrons) can form disjoint decision regions with arbitrary shapes in multidimensional cases, SLFN with some unbounded activation function can also form disjoint decision regions with arbitrary shapes