Adaptive higher-order feedforward neural networks

Author

Shuxiang Xu ; Ming Zhang

Author_Institution

Western Sydney Univ., Campbelltown, NSW

Volume

1

fYear

1999

fDate

6/21/1905 12:00:00 AM

Firstpage

328

Abstract

In this paper we study the approximation capabilities of an adaptive higher-order feedforward neural network (AHFNN) with a neuron-adaptive activation function. A learning algorithm is derived to tune the free parameters in the neuron-adaptive activation function as well as connection weights between neurons. Simulation results show that the proposed AHFNN presents several advantages over traditional neuron-fixed networks such as increased flexibility, much reduced network size, faster learning, and lessened approximation errors. Experiments also reveal that AHFNN is especially superior in financial data simulation and financial prediction

Keywords

adaptive systems; feedforward neural nets; learning (artificial intelligence); transfer functions; AHFNN; adaptive high-order feedforward neural networks; approximation capabilities; faster learning; financial data simulation; financial prediction; free parameter tuning; learning algorithm; lessened approximation errors; neuron-adaptive activation function; processing flexibility; reduced network size; Approximation error; Australia Council; Computer networks; Feedforward neural networks; Fuzzy control; Information systems; Neural networks; Neurons; Predictive models; Spline;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1999. IJCNN '99. International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-5529-6

Type

conf

DOI

10.1109/IJCNN.1999.831512

Filename

831512