This Artwork Does Not Exist

In analogy with "this person does not exist", Philip Wang, a 33 year old software engineer, added a new baby to his series of AI GAN generated images. My question at the time I discovered the "this person does not exist" website was obviously... what is next to be generated from scratch?

The answer is ART.

Indeed, we could not be left alone, and many questions are raised today. We could ask ourselves, since none of the artworks are real but still they are al unique, if there is a future for abstract paintings? Is AI generated art les valuable then the real? Can Ai be denominated as being artistic, or at least creative?

AI Rembrandt beekman foundation — A "new" Rembrandt portrait is actually the creation of a 3-D printer and a statistical analysis of 346 paintings.

Of course we would notice that these AI Artworks are only digital reproductions end have no life in the real? But no, we could easily 3D print these pictures just the same Ben Haanstra did, the end result of the project "The Next Rembrandt".

The best is yet to come, "this politician is not real".

A generative adversarial network (GAN) is a class of machine learning frameworks invented by Ian Goodfellow and his colleagues in 2014. Two neural networks contest with each other in a game (in the sense of game theory, often but not always in the form of a zero-sum game). Given a training set, this technique learns to generate new data with the same statistics as the training set. For example, a GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers, having many realistic characteristics. Though originally proposed as a form of generative model for unsupervised learning, GANs have also proven useful for semi-supervised learning,fully supervised learning,and reinforcement learning. In a 2016 seminar, Yann LeCun described GANs as "the coolest idea in machine learning in the last twenty years".

This Artwork Does Not Exist