Computer algorithm manages to paint in the style of artists like Turner and Munch

• Researchers created system that can interpret the styles of famous painters to transform a photograph into a digital painting
• Scientists replicated styles of Van Gogh, Turner, Kandinsky and Picasso
• Using what experts describe as a 'deep neural network', it is hoped that the software will shed light on how the human mind creates and perceives art 

It's a skill that we like to think of unique, if not sacred, to the human imagination. But painting awe-inspiring masterpieces might soon fall into the domain of robots too.

Researchers have created a system that can interpret the styles of famous artists to transform a photograph into a digital painting reminiscent of their specific style.

Scientists were able to replicate the signature brushstrokes of artists including Van Gogh, Turner, Kandinsky and Picasso.

Scientists used a dull-looking photograph of houses overlooking the Neckar River in Tubingen as their subject (top left). The system then translated the image into works by Vincent Van Gogh (bottom left), Edward Munch (bottom right) and JMW Turner (top right)

Using what experts describe as a 'deep neural network', it is hoped that the software will shed light on how the human mind creates and perceives art. 

The network is a form of machine learning that mimics the way a human brain recognises patterns.

The software can simulate the way neurons behave when they are stimulated with words, sounds, or in this case images.

Experts across the discipline say that the technology could help improve weather predictions as well as medical diagnosis. 

Scientists were also able to adjust the filter that was applied to the image - making it more or less like the style of the artist (Kandinsky effect being adjusted pictured)

They put the image through the system, along with an example of a masterpiece that acted as a classic example of an artist’s style (Pablo Picasso filter pictured left and  Wassily Kandinsky pictured right)

COULD APPLE PHONES HAVE ARTIFICIAL INTELLIGENCE?

Apple has ramped up its hiring of artificial intelligence experts, recruiting from PhD programs, posting dozens of job listings and greatly increasing the size of its AI staff, a review of hiring sites suggests and numerous sources confirm.
The goal is to challenge Google in an area the Internet search giant has long dominated: smartphone features that give users what they want before they ask.
As part of its push, the company is currently trying to hire at least 86 more employees with expertise in the branch of artificial intelligence known as machine learning, according to a recent analysis of Apple job postings.
The company has also stepped up its courtship of machine-learning PhD's, joining Google, Amazon, Facebook and others in a fierce contest, leading academics say.
But some experts say the iPhone maker's strict stance on privacy is likely to undermine its ability to compete in the rapidly progressing field.
Machine learning, which helps devices infer from experience what users are likely to want next, relies on crunching vast troves of data to provide unprompted services, such as the scores for a favorite sports team or reminders of when to leave for an appointment based on traffic. 

A similar network was used to create Google’s famous Deep Dream system, where images were turned into what looked like digital hallucinations. 

Google released its bizarre 'Inceptionist' images in June to show how computers are able to learn over time.

The firm trained an artificial neural network by showing it millions of images and then asked it to highlight areas that might, if only at a very abstract level, look like specific objects. 

This resulted in wildly distorted images filled with eyeballs and dogs.

In the new study researchers taught their system to process how artists used colour, shape, lines, and brushstrokes so that it could reinterpret images in the style of those artists, Quartz reported. 

Scientists used a dull-looking photograph of houses overlooking the Neckar River in Tübingen, Germany, as their subject.

They put the image through the system, along with an example of a masterpiece that acted as a classic example of an artist’s style.

The system then adjusted colours and introduced brushstrokes to the photograph - much like a Instagram filter - to make it look like it could have been painted by the artist.

Scientists were also able to make subtle adjustments to the filter, making it more or less like the style of the artist.

Scientists say that their work offers a 'path forward to an algorithmic understanding of how humans create and perceive artistic imagery'. 

Google released pictures earlier this year of images created in a similar way. The images were created by feeding a picture into the neural network, and asking emphasise feature it recognised - in this case, animals

The researchers taught the system to process how artists used colour, shape, lines, and brushstrokes so that it could reinterpret regular images in the style of those artists, Quartz reported