Architecture selection for networks trained with extreme learning machine using localized generalization error model

Authors:
Wang Xi-Zhao;Shao Qing-Yan;Miao Qing;Zhai Jun-Hai
Affiliations:
Key Lab. of Machine Learning and Computational Intelligence, College of Mathematics and Computer Science, Hebei University, Baoding, Hebei 071002, China;Key Lab. of Machine Learning and Computational Intelligence, College of Mathematics and Computer Science, Hebei University, Baoding, Hebei 071002, China;Key Lab. of Machine Learning and Computational Intelligence, College of Mathematics and Computer Science, Hebei University, Baoding, Hebei 071002, China;Key Lab. of Machine Learning and Computational Intelligence, College of Mathematics and Computer Science, Hebei University, Baoding, Hebei 071002, China
Venue:
Neurocomputing
Year:
2013

Citing 18
Cited 7

Neural networks and the bias/variance dilemma

Neural Computation
Unbiased estimate of generalization error and model selection in neural network

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Principles of Neurocomputing for Science and Engineering

Principles of Neurocomputing for Science and Engineering
An approach to guaranteeing generalisation in neural networks

Neural Networks
Letters: Convex incremental extreme learning machine

Neurocomputing
A definition of partial derivative of random functions and its application to RBFNN sensitivity analysis

Neurocomputing
Induction of multiple fuzzy decision trees based on rough set technique

Information Sciences: an International Journal
Feature selection using localized generalization error for supervised classification problems using RBFNN

Pattern Recognition
Enhanced random search based incremental extreme learning machine

Neurocomputing
Radial Basis Function network learning using localized generalization error bound

Information Sciences: an International Journal
Improving generalization of fuzzy IF-THEN rules by maximizing fuzzy entropy

IEEE Transactions on Fuzzy Systems
Error minimized extreme learning machine with growth of hidden nodes and incremental learning

IEEE Transactions on Neural Networks
OP-ELM: optimally pruned extreme learning machine

IEEE Transactions on Neural Networks
Constructive hidden nodes selection of extreme learning machine for regression

Neurocomputing
Learning capability and storage capacity of two-hidden-layer feedforward networks

IEEE Transactions on Neural Networks
Universal approximation using incremental constructive feedforward networks with random hidden nodes

IEEE Transactions on Neural Networks
Localized Generalization Error Model and Its Application to Architecture Selection for Radial Basis Function Neural Network

IEEE Transactions on Neural Networks

Direct Kernel Perceptron (DKP): Ultra-fast kernel ELM-based classification with non-iterative closed-form weight calculation

Neural Networks
Evolutionary ELM wrapper feature selection for Alzheimer's disease CAD on anatomical brain MRI

Neurocomputing
Extreme learning machines for soybean classification in remote sensing hyperspectral images

Neurocomputing
Fast prediction of protein-protein interaction sites based on Extreme Learning Machines

Neurocomputing
Online ship roll motion prediction based on grey sequential extreme learning machine

Neurocomputing
Hybrid extreme rotation forest

Neural Networks
Let a biogeography-based optimizer train your Multi-Layer Perceptron

Information Sciences: an International Journal

Quantified Score

Hi-index	0.01

Visualization

Abstract

The initial localized generalization error model (LGEM) aims to find an upper bound of error between a target function and a radial basis function neural network (RBFNN) within a neighborhood of the training samples. The contribution of LGEM can be briefly described as that the generalization error is less than or equal to the summation of three terms: training error, stochastic sensitivity measure (SSM), and a constant. This paper extends the initial LGEM to a new LGEM model for single-hidden layer feed-forward neural networks (SLFNs) trained with extreme learning machine (ELM) which is a type of new training algorithms without iterations. The development of this extended LGEM can provide some useful guidelines for improving the generalization ability of SLFNs trained with ELM. An algorithm for architecture selection of the SLFNs is also proposed based on the extended LGEM. Experimental results on a number of benchmark data sets show that an approximately optimal architecture in terms of number of neurons of a SLFN can be found using our method. Furthermore, the experimental results on eleven UCI data sets show that the proposed method is effective and efficient.