A Guide for the Upper Bound on the Number of Continuous-Valued Hidden Nodes of a Feed-Forward Network

Authors:
Rua-Huan Tsaih;Yat-Wah Wan
Affiliations:
Department of Management Information Systems, National Chengchi University, Taipei, Taiwan 116;Graduate Institute of Global Operations Strategy and Logistics Management, National Dong Hwa University, Taiwan 974
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Year:
2009

Citing 8
Cited 1

Introduction to the theory of neural computation

Introduction to the theory of neural computation
Feedforward nets for interpolation and classification

Journal of Computer and System Sciences
Original Contribution: Bounds on the number of hidden units in binary-valued three-layer neural networks

Neural Networks
Solving the N-bit parity problem using neural networks

Neural Networks
On the exact solution of the Parity-N problem using ordered neural networks

Neural Networks
A Solution for the N-bit Parity Problem Using a Single Translated Multiplicative Neuron

Neural Processing Letters
An explanation of reasoning neural networks

Mathematical and Computer Modelling: An International Journal
Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions

IEEE Transactions on Neural Networks

An Abductive-Reasoning Guide for Finance Practitioners

Computational Economics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study proposes and validates a construction concept for the realization of a real-valued single-hidden layer feed-forward neural network (SLFN) with continuous-valued hidden nodes for arbitrary mapping problems. The proposed construction concept says that for a specific application problem, the upper bound on the number of used hidden nodes depends on the characteristic of adopted SLFN and the observed properties of collected data samples. A positive validation result is obtained from the experiment of applying the construction concept to the m -bit parity problem learned by constructing two types of SLFN network solutions.