The technology behind the art is called a generative adversarial network (GAN). GANs are a type of AI that pits two neural networks against each other. One network generates images, and the other network judges whether or not those images are real. The two networks compete with each other to create better and better images.
GANs have been used to create art before, but the results were often blurry and abstract. The new AI is able to create images that are much more realistic. The AI was trained on a dataset of over 1 million images from the ImageNet database. It was then tasked with creating its own images based on what it learned from the dataset. The AI can be trained to create different types of art, including portraits, landscapes, and cityscapes.The researchers hope that their work will help inspire other researchers to use GANs for artistic purposes. They also hope that their work will help inspire people to think about how AI can be used in creative ways.
“I hope that our work will help to inspire other researchers to use GANs for artistic purposes,” said study author Ian Goodfellow. “I also hope that it will help people think about how AI can be used in creative ways.”
The researchers have made their code available on GitHub so that others can use it to create their own art.