DocumentCode :
1564031
Title :
An adaptive function neural network (ADFUNN) classifier
Author :
Kang, Miao ; Palmer-Brown, Dominic
Author_Institution :
Sch. of Comput., Leeds Metropolitan Univ.
Volume :
1
fYear :
2005
Firstpage :
586
Lastpage :
590
Abstract :
ADFUNN is based on a linear piecewise neuron activation function that is modified by a novel gradient descent supervised learning algorithm. It has been applied to some linearly inseparable problems: XOR, Iris dataset, phrase recognition problem. In all cases it exhibited impressive generalisation classification ability with no hidden nodes. In addition, the learned functions support intelligent data analysis. In this paper, we improve the general learning rule of ADFUNN by using proximal proportionality to adapt neural activation functions more accurately. The learned functions are then smoothed in preparation for recognising their closest fit to analytical functions. We compare two different algorithms for smoothing the learned function curves: the simple moving average and least-squares polynomial smoothing. The smoothed curves prove to be accurate replacements for the natural language phrase recognition test case
Keywords :
learning (artificial intelligence); neural nets; pattern classification; Iris dataset; XOR; adaptive function neural network classifier; gradient descent supervised learning algorithm; intelligent data analysis; learned function curves; least-squares polynomial smoothing; linear piecewise neuron activation function; natural language phrase recognition; neural activation functions; phrase recognition problem; proximal proportionality; Adaptive systems; Data analysis; Iris; Natural languages; Neural networks; Neurons; Polynomials; Smoothing methods; Supervised learning; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks and Brain, 2005. ICNN&B '05. International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9422-4
Type :
conf
DOI :
10.1109/ICNNB.2005.1614681
Filename :
1614681
Link To Document :
بازگشت