Redes Generativas Adversarias (GAN) Fundamentos Teóricos y Aplicaciones
It provides an introductory overview of GANs for the Spanish-speaking community, making scientific knowledge more accessible, but is incremental as it does not introduce new methods or results.
The article explains the theoretical foundations and basic architecture of Generative Adversarial Networks (GANs), a method for generating new data instances that resemble the training distribution, and highlights their applications in fields like computer vision and natural language processing.
Generative adversarial networks (GANs) are a method based on the training of two neural networks, one called generator and the other discriminator, competing with each other to generate new instances that resemble those of the probability distribution of the training data. GANs have a wide range of applications in fields such as computer vision, semantic segmentation, time series synthesis, image editing, natural language processing, and image generation from text, among others. Generative models model the probability distribution of a data set, but instead of providing a probability value, they generate new instances that are close to the original distribution. GANs use a learning scheme that allows the defining attributes of the probability distribution to be encoded in a neural network, allowing instances to be generated that resemble the original probability distribution. This article presents the theoretical foundations of this type of network as well as the basic architecture schemes and some of its applications. This article is in Spanish to facilitate the arrival of this scientific knowledge to the Spanish-speaking community.