A Deep Neural Network Model Based on a Mutation Operator

KIPS Transactions on Software and Data Engineering, Vol. 6, No.12, pp.573-580, December 2017
10.3745/KTSDE.2017.6.12.573, Full Text

Abstract

Deep Neural Network(DNN) is a large layered neural network which is consisted of a number of layers of non-linear units. Deep Learning which represented as DNN has been applied very successfully in various applications. However, many issues in DNN have been identified through past researches. Among these issues, generalization is the most well-known problem. A Recent study, Dropout, successfully addressed this problem. Also, Dropout plays a role as noise, and so it helps to learn robust feature during learning in DNN such as Denoising AutoEncoder. However, because of a large computations required in Dropout, training takes a lot of time. Since Dropout keeps changing an inter-layer representation during the training session, the learning rates should be small, which makes training time longer. In this paper, using mutation operation, we reduce computation and improve generalization performance compared with Dropout. Also, we experimented proposed method to compare with Dropout method and showed that our method is superior to the Dropout one.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from October 15, 2016)

Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


Cite this paper

[KIPS Transactions Style]
J. S. Ho and M. J. Sub, "A Deep Neural Network Model Based on a Mutation Operator," KIPS Transactions on Software and Data Engineering, Vol.6, No.12, pp.573-580, 2017, DOI: 10.3745/KTSDE.2017.6.12.573.

[IEEE Style]
Jeon Seung Ho and Moon Jong Sub, "A Deep Neural Network Model Based on a Mutation Operator," KIPS Transactions on Software and Data Engineering, vol. 6, no. 12, pp. 573-580, 2017. DOI: 10.3745/KTSDE.2017.6.12.573.

[ACM Style]
Ho, J. S. and Sub, M. J. 2017. A Deep Neural Network Model Based on a Mutation Operator. KIPS Transactions on Software and Data Engineering, 6, 12, (2017), 573-580. DOI: 10.3745/KTSDE.2017.6.12.573.