[ Schapire R E. The strength of w eak learnab ility [ J]. M achine Learn ing, 1990, 5( 2) : 197-227.
[2]
[ Zaknich A. In troduction to themod ified probab ilistic neural netwo rk for gene ra l s igna l pro cessing app lications[ J]. IEEE Transactions on S igna l Processing, 1998, 46( 7): 1 980-1 990.
[3]
[ Freund Y, Schap ire R. Expe rim en ts w ith a new boosting algor ithm [ C ] / / Sa itta L. Proc o f the 13th Int. 1 Conf onM achine Learning. Austin: M organ Kanfm ann, 1996: 148-156.
[4]
[ Liu B, H suW, M a Y. Prun ing and summ ar izing the d iscove red assoc ia tions[ Z] . KDD- 99, 1999.
[5]
[ 刘道群. 基于遗传神经网络的入侵检测模型的研究[ D]. 重庆: 重庆大学, 2005.
[6]
Liu Daoqun. S tudy o f IDS model based on genetic neura l network[ D]. Chongq ing: Chongqing Un iversity, 2005. ( in Chinese)
[7]
[ Jackson D A, Yong C. Robust pr inc ipal component analysis and outlier detection w ith eco log ical data[ J]. Env ironm etr ics,2004, 15( 2): 129-139.
[8]
[ Va liant L G. A theory of learnable[ J]. Commun ica tion o f ACM, 1984, 27( 11): 1 134-1 142.
