바로가기메뉴

본문 바로가기 주메뉴 바로가기

logo

A Study on the Development of DGA based on Deep Learning

Korean Journal of Artificial Intelligence / Korean Journal of Artificial Intelligence, (E)2508-7894
2017, v.5 no.1, pp.18-28
https://doi.org/https://doi.org/10.24225/kjai.2017.5.1.18
Park, Jae-Gyun
Choi, Eun-Soo
Kim, Byung-June
Zhang, Pan
  • Downloaded
  • Viewed

Abstract

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 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.

keywords
DGA, Deep Learning, Dropout, Genetic Algorithm, Overfitting, AI

Korean Journal of Artificial Intelligence