Introduction to Generative Adversarial Neural Networks (GANs) for Image and Data Generation (7.1)
Generative Adversarial Neural Networks (GANs) can generate fake data based on input data. The input data is often images, such as human faces. Two neural networks train as a pair. The generator learns to produce better images that might fool the discriminator. The discriminator learns to discriminate the images produces by them generator from real images.
Code for This Video:
https://github.com/jeffheaton/t81_558_deep_learning/blob/8466852fb7f85bc816dbd08102c10209d4719b16/t81_558_class_07_1_gan_intro.ipynb
Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/
Follow Me/Subscribe:
https://www.youtube.com/user/HeatonResearch
https://github.com/jeffheaton
https://twitter.com/jeffheaton
Support Me on Patreon: https://www.patreon.com/jeffheaton
Generative Adversarial Neural Networks (GANs) can generate fake data based on input data. The input data is often images, such as human faces. Two neural networks train as a pair. The generator learns to produce better images that might fool the discriminator. The discriminator learns to discriminate the images produces by them generator from real images.
Code for This Video:
https://github.com/jeffheaton/t81_558_deep_learning/blob/8466852fb7f85bc816dbd08102c10209d4719b16/t81_558_class_07_1_gan_intro.ipynb
Course Homepage: https://sites.wustl.edu/jeffheaton/t81-558/
Follow Me/Subscribe:
https://www.youtube.com/user/HeatonResearch
https://github.com/jeffheaton
https://twitter.com/jeffheaton
Support Me on Patreon: https://www.patreon.com/jeffheaton
