Abstract
We show a simplistic approach using simple Convolutional Neural Network (CNN) to classify Japanese handwritten digit dataset Kuzushiji-MNIST. We use combinations of loss functions and optimisers on an empirically sound model of Convolutional Neural Netwok (CNN) to come up with a new State-of-the-art accuracy for all Simple CNN approaches on the Kuzushiji-MNIST dataset with accuracy of 96.13 %.
A. Ghosh and A. Mukherjee—Both authors have contributed equally
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., Ha, D.: Deep Learning for Classical Japanese Literature. Cornell University (2018)
Chollet, F., et al.: Keras (2015). https://keras.io
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Deng, L.: The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process. Mag. 29(6), 141–142 (2012)
Kussul, E., Baidyk, T.: Improved method of handwritten digit recognition tested on MNIST database. Image Vis. Comput. 22(12), 971–981 (2004)
Keysers, D.: Comparison and combination of state-of-the-art techniques for handwritten character recognition: topping the MNIST Benchmark (2007)
Github link. https://github.com/rois-codh/kmnist
Hidasi, B., Karatzoglou, A.: Recurrent neural networks with top-k gains for session-based recommendations. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 843–852, October 2018
Tsai, C.: Recognizing handwritten Japanese characters using deep convolutional neural networks. University of Stanford in Stanford, California (2016)
Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors (2012)
Uchida, S., Ide, S., Iwana, B.K., Zhu, A.: A further step to perfect accuracy by training CNN with larger data. In: International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 405–410. IEEE (2016)
Wan, L., Zeiler, M., Zhang, S., Le Cun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: International Conference on Machine Learning, pp. 1058–1066 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ghosh, A., Mukherjee, A., Ghosh, C. (2020). Simplistic Deep Learning for Japanese Handwritten Digit Recognition. In: Dawn, S., Balas, V., Esposito, A., Gope, S. (eds) Intelligent Techniques and Applications in Science and Technology. ICIMSAT 2019. Learning and Analytics in Intelligent Systems, vol 12. Springer, Cham. https://doi.org/10.1007/978-3-030-42363-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-42363-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-42362-9
Online ISBN: 978-3-030-42363-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)