Citation :

AnNing, Mazida Ahmad, Huda lbrahim, 2024. "Generative Adversarial Networks: A Novel Approach to Generative Modeling" ESP International Journal of Advancements in Computational Technology (ESP-IJACT)  Volume 2, Issue 1: 38-43.

Abstract :

Generative Adversarial Networks (GANs) have emerged as a novel approach to generative modeling, revolutionizing the field of machine learning. GANs consist of two neural networks, a generator, and a discriminator, that are trained competitively. The generator attempts to produce synthetic data that is indistinguishable from real data, while the discriminator aims to correctly classify between real and fake data. This paper explores the key concepts and advancements in GANs, including different architectural variations and training strategies. Moreover, it analyzes the strengths and limitations of GANs in generating high-quality and diverse data samples. The experimental results demonstrate the effectiveness of GANs in various domains, such as image generation and text synthesis. In conclusion, GANs provide a promising solution for generative modeling, presenting great potential for applications in data augmentation, anomaly detection, and creative content generation.

References :

[1] A Wang. Application of Generative Adversarial Network on Image Style Transformation and Image Processing [D]., 2018

[2] R Anirudh,JJ Thiagarajan,B Kailkhura,et al.An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks[D].,2018

[3] K Shmelkov.Approches pour l'apprentissage incrémental et la génération des images [D]., 2019

[4] G Li,G Xu,H Qiu,et al.A Novel Verifiable Fingerprinting Scheme for Generative Adversarial Networks[D].,2021

[5] Shuqian Duan,Jiecheng Xiong,Hui Qian.Generative Adversarial Networks Based Stochastic Approach to the Modeling of Individual Jumping Loads[D].International Journal of Structural Stability & Dynamics,2020

[6] JL Wu, K Kashinath, A Albert, et al.Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems[D].Journal of Computational Physics,2019

[7] G Antipov.Apprentissage profond pour la description sémantique des traits visuels humains[D].,2017

[8] MVSS Raghavendra,T Genki,K Daisuke.Enhancing cryo-EM maps with 3D deep generative networks for assisting protein structure modeling[D].Bioinformatics,2023

[9] Zhang T F, Tilke P, Dupont E, et al.Generating geologically realistic 3D reservoir facies models using deep learning of sedimentary architecture with generative adversarial networks[J].Petroleum Science, 2019.DOI:CNKI:SUN:SYKX.0.2019-03-006.

[10] GoodfellowIan,Pouget-AbadieJean,MirzaMehdi,et al.Generative adversarial networks[D].Communications of the Acm,2020

[11] Yeji Kim,Gihun Joo,Jinho Joo,et al.PO-04-175 RECONSTRUCTING TWELVE-LEAD ELECTROCARDIOGRAM SIGNALS FROM A SINGLE-LEAD SIGNAL USING GENERATIVE ADVERSARIAL NETWORKS[D].,2023

[12] P Xie, J Hou, Y Yin.Seismic inverse modeling method based on generative adversarial networks[D].Journal of Petroleum Science & Engineering,2022

[13] SJ Barigye,GDL Vega,Y Perez-Castillo.Generative Adversarial Networks (GANs) Based Synthetic Sampling for Predictive Modeling[D].Molecular Informatics,2020

[14] Zhang, ZiqiYan, ChaoMesa, Diego A.Sun, JimengMalin, Bradley A..Ensuring electronic medical record simulation through better training, modeling, and evaluation[D].Journal of the American Medical Informatics Association,2020

[15] JZ Feng, MA Xiang-Cong, YK Liu, et al.Research on Generative Adversarial Networks of Named Entity Recognition[D].Journal of Chinese Computer Systems,2019

Keywords :

Generative Adversarial Networks, Generative Modeling, Neural Networks, Synthetic Data, Image Generation.