Education, Science, Technology, Innovation and Life
Open Access
Sign In

Machine learning: Training model with the case study

Download as PDF

DOI: 10.23977/jaip.2023.060808 | Downloads: 7 | Views: 268

Author(s)

Tianyue Jiang 1, Lihong Zhang 1

Affiliation(s)

1 Central University of Finance and Economics, Beijing, China

Corresponding Author

Tianyue Jiang

ABSTRACT

In recent decades, making machines learn from a massive dataset has become a prevalent task. It is significant to build a suitable deep learning model which would make its own decisions after training. This project aims to deal with a massive dataset with the trained deep learning model. More specifically, this project applies a Convolutional Neural Network (CNN) model to classify massive text data. It applies Generative Adversarial Network (GAN) model to regress image data. Furthermore, we start by building the model and enhance the model with necessary modifications for satisfying performance. Then we train and test the model to verify that the model achieves its aim. While the whole process implements based on Python and the Tensor Flow environment.

KEYWORDS

Machine learning, Deep learning, CNN, GAN

CITE THIS PAPER

Tianyue Jiang, Lihong Zhang, Machine learning: Training model with the case study. Journal of Artificial Intelligence Practice (2023) Vol. 6: 48-56. DOI: http://dx.doi.org/10.23977/jaip.2023.060808.

REFERENCES

[1] Ciregan, D., Meier, U., & Schmidhuber, J. (2012). Multi-column deep neural networks for image classification. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 3642–3649). https://doi.org/10.1109/CVPR.2012.6248110
[2] Deshpande Adit. (2016). A Beginner's Guide To Understanding Convolutional Neural Networks. Github, 19, 1–11. https://doi.org/10.1097/MD.0b013e31822403e9 
[3] Jia Deng, Wei Dong, Socher, R., Li-Jia Li, Kai Li, & Li Fei-Fei. (2009). ImageNet: A large-scale hierarchical image database (pp. 248–255). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ cvprw. 2009.5206848
[4] Davis, Ian. 2009. "The 'super-Resolution' Revolution." In Biochemical Society Transactions, 37:1042–1044. doi: 10.1042/BST0371042.
[5] Foroosh, H., Zerubia, J.B., Berthod, M., 2002. Extension of phase correlation to subpixel registration. IEEE Transactions on Image Processing 11, 188–199. doi:10.1109/83.988953
[6] Li, X., Chen, L., ... Tong, W., 2019. SCGAN: Disentangled Representation Learning by Adding Similarity Constraint on Generative Adversarial Nets. IEEE Access.7, 147928–147938. doi:10.1109/ACCESS.2018.2872695
[7] Pan, Z., Yu, W., ... Zheng, Y., 2019. Recent Progress on Generative Adversarial Networks (GANs): A Survey. IEEE Access 7, 36322–36333. doi:10.1109/ACCESS.2019.2905015
[8] MathWork, 2020. Create simple image classification network using deep network designer. https://www. mathworks.com/help/deeplearning/gs/create-simple-image-classification-network-using-deep-network-designer.html
[9] LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989). Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation, 1(4), 541–551. https://doi.org/10.1162/neco.1989.1.4.541

Downloads: 6056
Visits: 182427

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.