Abstract
The deep convolutional neural network (CNN) models are of great use in many areas and applications such as image processing and computer vision. The hyperparameter optimization in the CNN architectures is essential for an efficient implementation of model on software or hardware or “software-hardware co-design” platform to achieve better characteristics. In this paper, we have proposed CNN architecture models trained using MNIST dataset that explores the selection of various hyperparameters and their impact on the accuracy to achieve the hyperparameter optimization. The work presents thorough evaluation of various hyperparameters which offers a higher accuracy and keeps the architecture simple as compared with other published results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
J. Bergstra, Y. Bengio, Random search for hyperparameter optimization. J. Mach. Learn. Res. 13, 281–305 (2012)
T. Domhan, J.T. Springenberg, F. Hutter, Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves, in IJCAI International Joint Conference on Artificial Intelligence (2015)
S. Sanders, C.G. Carrier, Informing the use of hyperparameter optimization through meta-learning, in Proceedings—IEEE International Conference on Data Mining, ICDM, Nov 2017, vol. 2017 (2017), pp. 1051–1056
M. Claesen, B.D. Moor, Hyperparameter search in machine learning, in The XI Metaheuristics International Conference (2015)
N.M. Aszemi, P.D.D. Dominic, Hyperparameter optimization in convolutional neural network using genetic algorithms. Int. J. Adv. Comput. Sci. Appl. 10(6), 269–278 (2019)
Y. LeCun, L. Bottou, Y. Benjio, P. Haffner, Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)
Y. LeCun, Y. Bengio, G. Hinton, Deep learning. Nature 521(7553), 436–444 (2015)
A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (2012), pp. 1097–1105
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
S.S. Talathi, Hyper-parameter optimization of deep convolutional networks for object recognition, in IEEE International Conference on Image Processing (ICIP) (2015), pp. 3982–3986
F. Chen, N. Chen, H. Mao, H. Hu, Assessing four neural networks on handwritten digit recognition dataset (MNIST). Chuangxinban J. Comput. (2018)
B. Lopez, M.A. Nguyen, A. Walia, Modified MNIST. COMP 551, Group 11 (2019)
S. Ruder, An overview of gradient descent optimization algorithms (2016). arxiv:1609.04747
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Pandey, J., Asati, A.R., Shenoy, M.V. (2022). A Novel Method for Suitable Hyperparameter Selection in an Accurate Convolutional Neural Network Architecture. In: Saraswat, M., Roy, S., Chowdhury, C., Gandomi, A.H. (eds) Proceedings of International Conference on Data Science and Applications . Lecture Notes in Networks and Systems, vol 288. Springer, Singapore. https://doi.org/10.1007/978-981-16-5120-5_39
Download citation
DOI: https://doi.org/10.1007/978-981-16-5120-5_39
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5119-9
Online ISBN: 978-981-16-5120-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)