Large-margin and dropout learning of sum-product networks = Sum-Product Networks의 Large-Margin 기반 및 Dropout 학습법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 970
  • Download : 0
This paper investigates the generalization property of a sum-product network (SPN) in which the parameters are learned based on large-margin criterion and dropout. The learning criterion minimizes an objective function defined as a sum of an $L_{2}$ regularizer and a smooth hinge function of the margin that is defined as the smallest difference in unnormalized conditional probability between the true label and its closest competitor. The partial derivatives with respect to all the parameters of the SPN can be computed with backpropagation. To further improve the generalization of the SPN, the sum nodes (or max nodes in max-product network) are dropped out with Bernoulli distribution of a half during learning: dropout reduces overfitting by model-averaging. The large-margin based learning outperforms previously proposed discriminative learning of SPNs on CIFAR-10 and STL-10 for various training data size. The performance gain with large-margin learning increases with decrease in the number of training data. With dropout, the performance of large-margin is further improved for the two benchmark datasets.
Advisors
Yoo, Chang-Dongresearcher유창동
Description
한국과학기술원 : 미래자동차학제전공,
Publisher
한국과학기술원
Issue Date
2014
Identifier
592308/325007  / 020123606
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 미래자동차학제전공, 2014.8, [ iv, 33 p. ]

Keywords

딥 러닝; 드랍 아웃; 확장 마진; 합-곱 망 (SPNs); Dropout; Large-Margin; Sum-Product Networks (SPNs); Deep Learning

URI
http://hdl.handle.net/10203/197256
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=592308&flag=dissertation
Appears in Collection
PD-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0