An adaptive function neural network (ADFUNN) for phrase recognition

Author

Kang, Miao ; Palmer-Brown, Dominic

Author_Institution

Sch. of Comput., Leeds Metropolitan Univ., UK

Volume

1

fYear

2005

fDate

31 July-4 Aug. 2005

Firstpage

593

Abstract

We describe an adaptive function neural network (ADFUNN) by the authors (2005), and apply it to the natural language processing task of phrase recognition. ADFUNN is based on a linear piecewise neuron activation function that is modified by a novel gradient descent supervised learning algorithm. Linearly inseparable problems can he learned with ADFUNN, rapidly and without hidden neurons. We perform phrase recognition on a set of phrases from the Lancaster parsed corpus (LPC) by R. Garside, et al. (1987). Generalisation rises to 100% with 150 training patterns (out of a total of 254).

Keywords

generalisation (artificial intelligence); gradient methods; learning (artificial intelligence); natural languages; neural nets; Lancaster parsed corpus; adaptive function neural network; generalisation; gradient descent supervised learning algorithm; linear piecewise neuron activation function; natural language processing; phrase recognition; Adaptive systems; Biological neural networks; Biology computing; Computational intelligence; Computer networks; Electronic mail; Multilayer perceptrons; Neural networks; Neurons; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on

Print_ISBN

0-7803-9048-2

Type

conf

DOI

10.1109/IJCNN.2005.1555898

Filename

1555898