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

被引：5

作者：

Bodén, M ^{[1
]}

Hawkins, J ^{[1
]}

机构：

[1] Univ Queensland, Sch Informat Technol & Elect Engn, Brisbane, Qld 4072, Australia

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2005年 / 16卷 / 02期

关键词：

architectural bias; biological sequence; bioinformaties; recurrent neural network;

D O I：

10.1109/TNN.2005.844086

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：491 / 494

页数：4

共 9 条

[1] Exploiting the past and the future in protein secondary structure prediction
Baldi, P
Brunak, S
Frasconi, P
Soda, G
Pollastri, G
[J]. BIOINFORMATICS, 1999, 15 (11) : 937 - 946
[2] Toward a connectionist model of recursion in human linguistic performance
Christiansen, MH
Chater, N
[J]. COGNITIVE SCIENCE, 1999, 23 (02) : 157 - 205
[3] Recurrent neural networks with small weights implement definite memory machines
Hammer, B
Tino, P
[J]. NEURAL COMPUTATION, 2003, 15 (08) : 1897 - 1929
[4] Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
[5] KOLEN JF, 1994, PROCEEDINGS OF THE 1993 CONNECTIONIST MODELS SUMMER SCHOOL, P203
[6] Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles
Pollastri, G
Przybylski, D
Rost, B
Baldi, P
[J]. PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2002, 47 (02) : 228 - 235
[7] Learning nonregular languages: A comparison of simple recurrent networks and LSTM
Schmidhuber, J
Gers, F
Eck, D
[J]. NEURAL COMPUTATION, 2002, 14 (09) : 2039 - 2041
[8] Markovian architectural bias of recurrent neural networks
Tino, P
Cernansky, M
Benusková, L
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2004, 15 (01): : 6 - 15
[9] Architectural bias in recurrent neural networks: Fractal analysis
Tino, P
Hammer, B
[J]. NEURAL COMPUTATION, 2003, 15 (08) : 1931 - 1957

← 1 →