TARU PUBLICATIONS
Journal of Information and Optimization Sciences cover

Journal of Information and Optimization Sciences

(Since 1980)
Open Access ·Peer-reviewed·ISSN (Online): 2169-0103·ISSN (Print): 0252-2667

WoS  JIF 2026 : 0.4 (Q4)

Powered by:Powered by

Monthly Journal: Publishes theoretical and applied research on topics in information and optimization sciences.

Issues up to 2022 co-published with and available at:Taylor & Francis
submissions@tarupublications.com
Taru Online First Current IssueSpecial IssuesBrowse all Issues
Journal of Information and Optimization Sciences
Open Access Research Article

Decipherment of script : Using synthetic data generator’s

* ,

* Corresponding author · click or hover a name for details

pp. 783–791Vol. 46Issue 3April 2025DOI: 10.47974/JIOS-1797XML
Received:
11 Sep 2024
Published Online:
05 Apr 2025
Article type:
Research Article
Language:
EN
Article no.:
JIOS-1797
Pages:
783–791

Abstract

This paper is created to give a brief idea about the generative adversarial networks and the handwritten digits recognition using the synthetic data generators with the MNIST data. In this paper Tensorflow is used along with GAN’s to recognise the handwritten digits. The 2014 introduction of Generative Adversarial Networks (GANs) by Lan J. Goodfellow revolutionized deep learning and artificial intelligence. A subclass of generative models known as GANs uses a dual neural network structure—a generator and a discriminator—to transform unsupervised learning. GANs create varied, real data samples, influencing the design, entertainment, and healthcare sectors. They are employed in a variety of fields, notably text-to-image translation and image processing. Deep learning relies heavily on neural networks, which are also used in pattern analysis and picture identification. The generative models that are discussed here produce data that is similar to the source datasets and is categorized using density estimation. One popular kind of GANs is made up of a discriminator that separates created data from real data and a generator that produces synthetic data[5][[9]. Their adversarial training improves the discriminator’s ability to distinguish between actual and false samples while honing the generator’s capacity to generate realistic data. Neural network activation factors introduce non-linearity; their applicability varies throughout models and tasks. An open-source package called TensorFlow makes GANs and other AI tasks easier[3][15]. Using the MNIST dataset, an experiment demonstrating handwritten digit recognition using TensorFlow and the Rectified Linear Unit (ReLu) activation function is presented. After several epochs, the results show a significant improvement, demonstrating the effectiveness of GANs in picture identification.

Keywords

Neural networksCNNPerceptronGenerative modelGANActivation function

Subject Classifications

G06N 3/04

References

[1] A. Creswell, T. White, V. Dumoulin, K. Arulkumaran, B. Sengupta, and A. A. Bharath, “Generative adversarial networks: An overview,” IEEE Signal Process. Mag., vol. 35, no. 1, pp. 53–65 (2018).
[2] X. Guo and L. Zhao, “A systematic survey on deep generative models for graph generation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 5, pp. 5370–5390 (2022).
[3] G. T. V. Eswar and P. K. Singh, “Understanding taxonomy of generative models,” Lampyrid: J. Bioluminescent Beetle Res., vol. 13, pp. 598–604 (2023).
[4] T. Karras, S. Laine, and T. Aila, “A style-based generator architecture for generative adversarial networks,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pp. 4401–4410 (2019).
[5] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, et al., “Generative adversarial nets,” Adv. Neural Inf. Process. Syst., vol. 27  (2014).
[6] H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, “Self-attention generative adversarial networks,” in Int. Conf. Mach. Learn., pp. 7354–7363, PMLR, May(2019).
[7] X. Wang, K. Yu, S. Wu, J. Gu, Y. Liu, C. Dong, et al., “ESRGAN: Enhanced super-resolution generative adversarial networks,” in Proc. Eur. Conf. Comput. Vis. (ECCV) Workshops, pp. 0–0 (2018).
[8] A. Jabbar, X. Li, and B. Omar, “A survey on generative adversarial networks: Variants, applications, and training,” ACM Comput. Surv., vol. 54, no. 8, pp. 1–49 (2021).
[9] A. Sajeeda and B. M. Hossain, “Exploring generative adversarial networks and adversarial training,” Int. J. Cogn. Comput. Eng., vol. 3, pp. 78–89 (2022).
[10] A. Radford, L. Metz, and S. Chintala, “Unsupervised representation learning with deep convolutional generative adversarial networks,” arXiv preprint arXiv:1511.06434 (2015).
[11] T. Chavdarova and F. Fleuret, “SGAN: An alternative training of generative adversarial networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 9407–9415 (2018).
[12] D. Saxena and J. Cao, “Generative adversarial networks (GANs): Challenges, solutions, and future directions,” ACM Comput. Surv., vol. 54, no. 3, pp. 1–42(2021).
[13] T. Chavdarova and F. Fleuret, “SGAN: An alternative training of generative adversarial networks,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 9407–9415 (2018).
[14] D. Saxena and J. Cao, “Generative adversarial networks (GANs): challenges, solutions, and future directions,” ACM Comput. Surveys (CSUR), vol. 54, no. 3, pp. 1–42 (2021).
[15] Z. Deng, H. Zhang, X. Liang, L. Yang, S. Xu, J. Zhu, and E. P. Xing, “Structured generative adversarial networks,” Advances in Neural Information Processing Systems, vol. 30 (2017).

Views: 219Downloads: 90Citations: 0