The Register reports Google's "deep learning" decision-making computer clusters have become so good at their task that they're now capable of cracking coding problems that Google's top engineers can't. The software is used to identify objects in photos. For instance, Google engineers find it really hard to write a program that can identify paper shredders but the smart learning system is capable of picking out features in paper shredders that people can't easily spot and is capable of achieving a greater success rate than the search giant's top engineers.
What stunned Quoc V. Le is that the software has learned to pick out features in things like paper shredders that people can't easily spot – you've seen one shredder, you've seen them all, practically. But not so for Google's monster.
Learning "how to engineer features to recognize that that's a shredder – that's very complicated," he explained. "I spent a lot of thoughts on it and couldn't do it."
It started with a GIF: Image recognition paves way for greater things
Many of Quoc's pals had trouble identifying paper shredders when he showed them pictures of the machines, he said. The computer system has a greater success rate, and he isn't quite sure how he could write program to do this.
"We had to rely on data to engineer the features for us, rather than engineer the features ourselves," Quoc explained.