A functions localized neural network with branch gates

Authors:
Qingyu Xiong;Kotaro Hirasawa;Jinglu Hu;Junichi Murata
Affiliations:
Automation College, Chongqing University, Chongqing, People's Republic of China;Graduate School of Information, Production and Systems, Waseda University, Hibikino 2-7, Wakamatsu-ku, Kitakyushu, Fukuoka 808-0135, Japan;Graduate School of Information, Production and Systems, Waseda University, Hibikino 2-7, Wakamatsu-ku, Kitakyushu, Fukuoka 808-0135, Japan;Graduate School of Information Science and Electrical Engineering, Kyushu University, 6-10-1 Hakozaki, Higashiku, Fukuoka 812-8581, Japan
Venue:
Neural Networks
Year:
2003

Citing 13
Cited 1

Multilayer feedforward networks are universal approximators

Neural Networks
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
The cascade-correlation learning architecture

Advances in neural information processing systems 2
The roots of backpropagation: from ordered derivatives to neural networks and political forecasting

The roots of backpropagation: from ordered derivatives to neural networks and political forecasting
Hierarchical mixtures of experts and the EM algorithm

Neural Computation
Trajectory production with the adaptive time-delay neural network

Neural Networks
Universal learning network and its application to chaos control

Neural Networks
Improvement of generalization ability for identifying dynamical systems by using universal learning networks

Neural Networks
Learning Petri network and its application to nonlinear systemcontrol

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Universal learning network and its application to robust control

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Circular backpropagation networks for classification

IEEE Transactions on Neural Networks
Representation and generalization properties of class-entropy networks

IEEE Transactions on Neural Networks
Exploring constructive cascade networks

IEEE Transactions on Neural Networks

Variations of the two-spiral task

Connection Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a functions localized network with branch gates (FLN-bg) is studied, which consists of a basic network and a branch gate network. The branch gate network is used to determine which intermediate nodes of the basic network should be connected to the output node with a gate coefficient ranging from 0 to 1. This determination will adjust the outputs of the intermediate nodes of the basic network depending on the values of the inputs of the network in order to realize a functions localized network. FLN-bg is applied to function approximation problems and a two-spiral problem. The simulation results show that FLN-bg exhibits better performance than conventional neural networks with comparable complexity.