New Approach to Optimize the Size of Convolution Mask in Convolutional

Young-Tae Kwak (곽영태)

New Approach to Optimize the Size of Convolution Mask in Convolutional

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2016, 21(1), pp.1-8
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science

Young-Tae Kwak ¹

¹전북대학교

Accredited

ABSTRACT

Convolutional neural network (CNN) consists of a few pairs of both convolution layer and subsampling layer. Thus it has more hidden layers than multi-layer perceptron. With the increased layers, the size of convolution mask ultimately determines the total number of weights in CNN because the mask is shared among input images. It also is an important learning factor which makes or breaks CNN's learning. Therefore, this paper proposes the best method to choose the convolution size and the number of layers for learning CNN successfully. Through our face recognition with vast learning examples, we found that the best size of convolution mask is 5 by 5 and 7 by 7, regardless of the number of layers. In addition, the CNN with two pairs of both convolution and subsampling layer is found to make the best performance as if the multi-layer perceptron having two hidden layers does.

KEYWORDS

Convolutional Neural Network, Convolution Mask, Convolution Layer

Citation status

* References for papers published after 2023 are currently being built.

[book] D. E. Rumelhart / 1986 / Parallel Distributed Processing: Explorations in the Microstructure of Cognition / Bradford Books : 318~362

[book] S. E. Fahlman / 1990 / Neural Information Processing System 2 / Morgan Kaufman : 524~532

[confproc] M. Riedmiller / 1993 / A direct adaptive method of faster backpropagation learning: The RPROP algorithm / Proc. IEEE Int. Conf. Neural Netw. : 586~591

[book] E. K. P. Chong / 1996 / An Introduction to Optimization / Wiley

[journal] M. T. Hagan / 1994 / Training feedforward networks with the Marquardt algorithm / IEEE Trans. Neural Netw 5(6) : 989~993

[book] Y. LeCun / 1990 / Advances in Neural Information Processing Systems (NIPS 1989) / Morgan Kaufman

[journal] S. Lawrence / 1997 / Face recognition: a convolutional neural-network approach / IEEE Transactions on Neural Networks / Institute of Electrical and Electronics Engineers (IEEE) 8(1) : 98~113

[confproc] LeCun, Yann / 2010 / Convolutional networks and applications in vision / Circuits and Systems (ISCAS), Proceedings of 2010 IEEE International Symposium on. IEEE

[journal] J. Villiers / 1993 / Backpropagation Neural Nets with One and Two Hidden Layers / IEEE Trans. Neural Netwoks 4(1) : 136~141

[web] S. L. Phung / ”MATLAB library for convolutional neural network,” Technical Report, ICT Research Institute, Visual and Audio Signal Processing Laboratory, University of Wollongong / http://www.uow.edu.au/˜phung

[journal] S. L. Phung / 2005 / Skin segmentation using color pixel classification: analysis and comparison / IEEE Transactions on Pattern Analysis and Machine Intelligence 27(1) : 148~154

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65