International Journal of Computational Linguistics Research

DLINE Journals portal

Home

New Journals

Browse Journals

Journal Prices

For Authors

Print ISSN: 0976-416X
Online ISSN: 0976-4178

About IJCLR
	DLINE Portal Home Home Aims & Scope Editorial Board Current Issue Next Issue Previous Issue Sample Issue Upcoming Conferences Self-archiving policy Alert Services Be a Reviewer Publisher Paper Submission Subscription Contact us

How To Order
	Order Online Price Information Request for Complimentary Print Copy

For Authors
	Guidelines for Contributors Online Submission Call for Papers Author Rights

RELATED JOURNALS

Journal of Digital Information Management (JDIM)

Journal of Multimedia Processing and Technologies (JMPT)

International Journal of Web Application (IJWA)

International Journal of Computational Linguistics Research

Computation Graphs use in the Neural Networks for Handwritten Digit Recognition

Ivaylo Penev and Milena Karova
Technical University of Varna 1 Studentska strVarna 9010, Bulgaria

Abstract: Neural networks have promises for developing handwritten digit processing and hence in this paper, we have given model for training. In this work we have used computation graphs for training and measuring the neural network. The features of the propose system is that it speed up the network building and training processing, and resulted in the new network model in the runtime environment. We have explained how we build the computation graphs while developing neural network and training. We have carried out experimental tests and described the use of data for handwritten digits training.

Keywords: Machine Learning, Neural Networks, Computation Graphs, Classification, Recognition, Parallel Calculation Computation Graphs use in the Neural Networks for Handwritten Digit Recognition

DOI:https://doi.org/10.6025/jcl/2021/12/3/69-76

Full_Text PDF 0.99 MB Download: 119 times

References:

[1] Ciresan, D., Meier, U., Gambardella, L., Schmidhuber, J. (2010). Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition, Neural Computation, Vol. 22, MIT, USA.
[2] Cire_an, D., Meier, U., Schmidhuber, J. (2012). Multi-column Deep Neural Networks for Image Classification, Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference, DOI: 10.1109/CVPR.2012.6248110, IEEE, 2012.
[3] Sato, I., Nishimura, H., Yokoi, K. (2015). APAC: Augmented Pattern Classification with Neural Networks, https://arxiv.org/abs/1505.03229, 2015.
[4] Chang, J.-R., Chen, Y.-S. (2015). Batch-normalized Maxout Network in Network, https://arxiv.org/abs/1511.02583, 2015.
[5] Chen-Yu, L., Gallagher, P., Zhuowen, T. (2015). Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree, https://arxiv.org/abs/1509.08985.
[6] Abadi, M., Agarwal, A., et. al. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, arXiv:1603.04467v2.
[7] Basit, N., Zhang, Y., Wu, H., Liu, H., Bin, J., He, Y., Hendawi, A. (2016). MapReduce-based deep learning with handwritten digit recognition case study, Big Data (Big Data), 2016 IEEE International Conference, DOI: 10.1109/BigData.2016.7840783, IEEE.
[8] http://yann.lecun.com/exdb/mnist/

DLINE Journals portal