An introduction to recursive neural networks and kernel methods for cheminformatics

被引：8

作者：

Micheli, Alessio

Sperduti, Alessandro

Starita, Antonina

机构：

[1] Univ Pisa, Dipartimento Informat, I-56127 Pisa, Italy

[2] Univ Padua, Dipartimento Matemat Pura & Applicata, I-35131 Padua, Italy

来源：

CURRENT PHARMACEUTICAL DESIGN | 2007年 / 13卷 / 14期

关键词：

QSAR/QSPR; recursive neural networks; kernel for structures; kernel methods; learning in structured domains; machine learning;

D O I：

10.2174/138161207780765981

中图分类号：

R9 [药学];

学科分类号：

1007 ;

摘要：

The aim of this paper is to introduce the reader to new developments in Neural Networks and Kernel Machines concerning the treatment of structured domains. Specifically, we discuss the research on these relatively new models to introduce a novel and more general approach to QSPR/QSAR analysis. The focus is on the computational side and not on the experimental one.

引用

页码：1469 / 1495

页数：27

共 86 条

[1] [Anonymous], LECT NOTES CONTROL I
[2] [Anonymous], 1991, Advances in Neural Information Processing Systems
[3] The principled design of large-scale recursive neural network architectures-DAG-RNNs and the protein structure prediction problem
Baldi, P
Pollastri, G
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2004, 4 (04) : 575 - 602
[4] Baldi P., 1998, Bioinformatics: The machine learning approach
[5] Baldwin J, 1999, CFO-MAG SR FINANC EX, V15, P11
[6] The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network
Bartlett, PL
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 1998, 44 (02) : 525 - 536
[7] BERNAZZANI L, 2004, 13 INT C THERM AN CH
[8] BERNAZZANI L, 2004, TR0416 U PIS DIP INF
[9] BIANCHINI M, 2002, P WCCI IJCNN 2002, V1, P154
[10] Bianucci AM, 1998, IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, P117, DOI 10.1109/IJCNN.1998.682247

← 1 2 3 4 5 6 7 8 9 →