[ad_1]
An impression generated with machine learning raised $ 432,500 at Christie's auction house in New York, for a total of 380,705 euros. It's more than forty times more than expected. A collective worked on it for months.
Although artificial intelligence can make independent art, the three men of the French collective Evident have opted for a different approach. Using generative contradictory networks, they made a series of eleven portraits of a fictional family
. The portrait of "Edmond de Belamy & # 39; reported $ 432,500. It is signed with the mathematical formula that describes the algorithm used in the generation. Hugo Caselles-Dupré, a machine learning student, explains to the motherboard that it took months to train the models, adjust the parameters and select the right input data.
The end result is the result of many iterations where human taste always plays a major role. In generative accusative networks, there are two models that compete, one generating and the other evaluating. The machine learning technique is most often used to generate realistic human images, although Edmond de Belamy also somewhat recalls the result of the failed restoration of a fresco by Jesus, now more known under the same name, observes Motherboard. [19659005] Edmond de Belamy obvious "width =" 656 "height =" 369 "/>
Source link
