10.txt

This complete matlab for neural network

发信人: GzLi (笑梨), 信区: DataMining
标  题: into. to SVM for DM (zz)
发信站: 南京大学小百合站 (Tue Oct 15 01:02:54 2002), 站内信件


http://www.cs.ucl.ac.uk/staff/r.burbidge/pubs/yor12-svm-intro.html


An Introduction to Support Vector Machines for Data Mining

 

Robert Burbidge, Bernard Buxton

Computer Science Dept., UCL, Gower Street, WC1E 6BT, UK.

 

Abstract

With increasing amounts of data being generated by businesses and researchers
 there is a need for fast, accurate and robust algorithms for data analysis. 
 Improvements in databases technology, computing performance and artificial i
ntelligence have 
contributed to the development of intelligent data analysis.  The primary aim
 of data mining is to discover patterns in the data that lead to better under
standing of the data generating process and to useful predictions.  Examples 
of applications of 
data mining include detecting fraudulent credit card transactions, character 
recognition in automated zip code reading, and predicting compound activity i
n drug discovery.  Real-world data sets are often characterized by having lar
ge numbers of 
examples, e.g. billions of credit card transactions and potential ‘drug-like
’ compounds; being highly unbalanced, e.g. most transactions are not fraudul
ent, most compounds are not active against a given biological target; and, be
ing corrupted by 
noise.  The relationship between predictive variables, e.g. physical descript
ors, and the target concept, e.g. compound activity, is often highly non-line
ar.  One recent technique that has been developed to address these issues is 
the support vector 
machine.  The support vector machine has been developed as robust tool for cl
assification and regression in noisy, complex domains.  The two key features 
of support vector machines are generalization theory, which leads to a princi
pled way to choose an 
hypothesis; and, kernel functions, which introduce non-linearity in the hypot
hesis space without explicitly requiring a non-linear algorithm.  In this tut
orial I introduce support vector machines and highlight the advantages thereo
f over existing data 
analysis techniques, also are noted some important points for the data mining
 practitioner who wishes to use support vector machines.

 --               ***  端庄厚重 谦卑含容 事有归着 心存济物  *** 数据挖掘  
http://[e-mail]/ 

※ 来源:．南京大学小百合站 bbs.nju.edu.cn．[FROM: 211.80.38.29]