Feedforward networks training speed enhancement by optimal initialization of the synaptic coefficients

Authors:
J. Y.F. Yam;T. W.S. Chow
Affiliations:
Dept. of Electron. Eng., City Univ. of Hong Kong, Kowloon;-
Venue:
IEEE Transactions on Neural Networks
Year:
2001

Citing 0
Cited 8

A People-Counting System Using a Hybrid RBF Neural Network

Neural Processing Letters
Sigmoidal Function Classes for Feedforward Artificial Neural Networks

Neural Processing Letters
A Modified Backpropagation Training Algorithm for Feedforward Neural Networks

Neural Processing Letters
Machine learning: a review of classification and combining techniques

Artificial Intelligence Review
Small Number of Hidden Units for ELM with Two-Stage Linear Model

IEICE - Transactions on Information and Systems
A Master-Slave Neural Network for precise recognition of the complicated hand operations based on EEG

International Journal of Advanced Media and Communication
Supervised Machine Learning: A Review of Classification Techniques

Proceedings of the 2007 conference on Emerging Artificial Intelligence Applications in Computer Engineering: Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies
Neighborhood based modified backpropagation algorithm using adaptive learning parameters for training feedforward neural networks

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This letter aims at determining the optimal bias and magnitude of initial weight vectors based on multidimensional geometry. This method ensures the outputs of neurons are in the active region and the range of the activation function is fully utilized. In this letter, very thorough simulations and comparative study were performed to validate the performance of the proposed method. The obtained results on five well-known benchmark problems demonstrate that the proposed method deliver consistent good results compared with other weight initialization methods