Java Deep Learning Projects

GANs

GANs are deep neural net architectures that consist of two networks pitted against each other (hence the name adversarial). Ian Goodfellow et al. introduced GANs in a paper (see more at https://arxiv.org/abs/1406.2661v1). GAN is one of the best research outcomes in AI that can learn to mimic any distribution of data. This is such that a trained GAN can be deployed to create worlds similar to our own, especially for images, music, speech, or prose.

Although the original GAN paper targeted simple image generation such as DCGAN, BEGAN, and so on, people are extending the idea for font generation, anime character generation, interactive image generation, text-to-image generation, 2D object generation, human pose estimation, and so on. A ...