Improved access to sequential motifs: a note on the architectural bias of recurrent networks

Author

Bodén, Mikael ; Hawkins, John

Author_Institution

Sch. of Inf. Technol. & Electr. Eng., Univ. of Queensland, Brisbane, Australia

Volume

16

Issue

2

fYear

2005

fDate

3/1/2005 12:00:00 AM

Firstpage

491

Lastpage

494

Abstract

For many biological sequence problems the available data occupies only sparse regions of the problem space. To use machine learning effectively for the analysis of sparse data we must employ architectures with an appropriate bias. By experimentation we show that the bias of recurrent neural networks-recently analyzed by Tino et al. and Hammer and Tino-offers superior access to motifs (sequential patterns) compared to the, in bioinformatics, standardly used feedforward neural networks.

Keywords

biology computing; feedforward neural nets; learning (artificial intelligence); pattern recognition; recurrent neural nets; bioinformatics; biological sequence problem; feedforward neural network; machine learning; recurrent neural network; sequential pattern; sparse data; Amino acids; Australia; Bioinformatics; Data analysis; Feedforward neural networks; History; Information technology; Machine learning; Neural networks; Recurrent neural networks; Architectural bias; bioinformatics; biological sequence; recurrent neural network; Computational Biology; Entropy; Neural Networks (Computer); Sequence Analysis;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2005.844086

Filename

1402509