Earticle

초록

영어

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA(Dropout Genetic Algorithm) which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.

목차

Abstract
 1. Introduction
 2. DGA (Dropout Genetic Algorithm)
  2-1. Genetic Algorithm
  2-2. Dropout
  2-3. DGA (Dropout Genetic Algorithm) Suggestion
 3. Experiments and Results
  3-1. Experimental Environment
  3-2. Experimental Result
 4. Conclusion
 References

키워드

저자

• Jae-Gyun Park [ Department of Medical IT Marketing, Eulji University, Korea ]
• Eun-Soo Choi [ Department of Medical IT Marketing, Eulji University, Korea ]
• Min-Soo Kang [ Department of Medical IT Marketing, Eulji University, Korea ] Corresponding author
• Yong-Gyu Jung [ Department of Medical IT Marketing, Eulji University, Korea ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Advanced Culture Technology(IJACT)

• 간기

  계간

• pISSN

  2288-7202

• eISSN

  2288-7318

• 수록기간

  2013~2025

• 등재여부

  KCI 등재

• 십진분류

  KDC 600 DDC 700