Adversarial machine learning has other uses besides generative modeling and can be applied to models other than neural networks. The general idea of learning via competition between players dates back to at least 1959 with the influential work of Arthur Samuel, demonstrating that algorithms could learn to play checkers via adversarial self-play.

Ian Goodfellow is recognized by several sources as having invented GANs in 2014. This paper included the first working implementation of a generative model based on adversarial networks, as well as game theoretic analysis establishing that the method is sound. However, there are several independent debates over who invented which aspects of GANs.

Some review papers about GANs from academic sources, such as assign credit for the idea to Ian Goodfellow and make no mention of Juergen Schmidhuber. Ian Goodfellow's own peer-reviewed GAN paper[1] mentions Schmidhuber's unsupervised adversarial technique called predictability minimization (PM), claiming that PM is not a minimax game. Schmidhuber disputes this claim, citing Equation 2 of the 1996 paper on PM. He also formulates

GANs as special cases of his Adversarial Curiosity (1990). Schmidhuber interrupted[46] a presentation by Goodfellow in 2016 demanding more credit for his earlier work. Goodfellow himself states that the most direct inspiration for GANs was noise-contrastive estimation, which uses the same loss function as GANs and which Goodfellow studied during his PhD in 2010-2014.

Other people had similar ideas but did not develop them similarly. An idea involving adversarial networks was published in a 2010 blog post by Olli Niemitalo. This idea was never implemented and did not involve stochasticity in the generator and thus was not a generative model. It is now known as a conditional GAN or cGAN.

An idea similar to GANs was used to model animal behavior by Li, Gauci and Gross in 2013.

In 2017, a GAN was used for image enhancement focusing on realistic textures rather than pixel-accuracy, producing a higher image quality at high magnification. In 2017,

the first faces were generated. These were exhibited in February 2018 at the Grand Palais. Faces generated by StyleGAN[55] in 2019 drew comparisons with deepfakes.

Beginning in 2017, GAN technology began to make its presence felt in the fine arts arena with the appearance of a newly developed implementation which was said to have crossed the threshold of being able to generate unique and appealing abstract paintings, and thus dubbed a "CAN", for "creative adversarial network".

A GAN system was used to create the 2018 painting Edmond de Belamy, which sold for US$432,500.[60] An early 2019 article by members of the original CAN team discussed further progress with that system, and gave consideration as well to the overall prospects for an AI-enabled art.

In May 2019, researchers at Samsung demonstrated a GAN-based system that produces videos of a person speaking given only a single photo of that person.

References