Cambridge scientists working with colleagues from the Studio Prisma announced the creation of a new type of artificial intelligence. He was called “Vincent” for a penchant for expression and the initiative system is not dutifully performs the job person, it is designed to seek to draw on their own. This is one of the firstborn of the concept of multi-AI unthinkable for yesterday’s technology.

The developers of “Vincent” has United in one system two methods of machine learning. “Technical” half responsible for image processing – II fed countless samples of painting and drawing techniques from the Renaissance to Picasso. The result is a robotic stylus “Vincent” can draw in any known style. The “emotional” part is built on the advanced experimental technology and on the course analyzes the actions of the artist, tries to understand his intentions and turn simple the first line in a finished drawing.

“Vincent” is useless to give a specific command, it operates independently and in parallel with the artist-man. If the AI is struggling to create, but still can not shake the chains of limitation – he needs to give at least a few lines the basis that on its basis he created the painting. But what, exactly, to predict extremely difficult, as the “way of thinking” “Vincent” is very reminiscent of the vagaries of undiscovered talent.

The combination of two machine learning systems that cater to different aspects of work to produce a single result – this is a multi-AI, in a simplified form. For example, a AI robot-the driver will be able to combine the transportation of fragile goods from an independent analysis of traffic on the road. Complex, controversial, yet interesting future of artificial intelligence.

Source — Cambridge Consulting