Abstract
Recently, neural networks are used in various applications to solve complex problems. The neural network creates models that can solve problems through training from data. However, overfitting problems in training models have a significant impact on the performance of a neural network. In this paper, the effect of dropout to reduce overfitting in neural networks is analyzed through experiments. It also analyzes the effect on the performance of neural networks according to the number of nodes in layers that is an important factor in designing neural network models. The results of these experiments will help to design the dropout rates and the number of nodes in layers to apply neural networks in various applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Murphy KP (2012) Machine learning: a probabilistic perspective. The MIT Press
Salman S, Liu X (2019) Overfitting mechanism and avoidance in deep neural networks. arXiv:1901.06566
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958
Baldi P, Sadowski P (2013) Understanding dropout. In: Proceedings of the 26th international conference on neural information processing systems, pp 2814–2822
Duyck J, Lee MH, Lei E (2014) Modified dropout for training neural network
Labach A, Salehinejad H, Valaee S (2019) Survey of dropout methods for deep neural networks. arXiv:1904.13310
LeCun Y, Cortes C, Burges C (2020) The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/
Acknowledgments
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Education) (No. NRF-2017R1D1A1B03034769).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lim, Hi. (2021). A Study on Dropout Techniques to Reduce Overfitting in Deep Neural Networks. In: Park, J.J., Loia, V., Pan, Y., Sung, Y. (eds) Advanced Multimedia and Ubiquitous Engineering. Lecture Notes in Electrical Engineering, vol 716. Springer, Singapore. https://doi.org/10.1007/978-981-15-9309-3_20
Download citation
DOI: https://doi.org/10.1007/978-981-15-9309-3_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-9308-6
Online ISBN: 978-981-15-9309-3
eBook Packages: EngineeringEngineering (R0)