Would You Like To Play A Game?



Games Find above Nature journal's own mini-documentary about DeepMind's proficiency in playing computer games (here a link to the paper). The story has been all over the intelligent media this past couple of days. Here's a version from The New Yorker:
"Deep neural networks rely on layers of connections, known as nodes, to filter raw sensory data into meaningful patterns, just as neurons do in the brain. Apple’s Siri uses such a network to decipher speech, sorting sounds into recognizable chunks before drawing on contextual clues and past experiences to guess at how best to group them into words. Siri’s deductive powers improve (or ought to) every time you speak to her or correct her mistakes. The same technique can be applied to decoding images. To a computer with no preĆ«xisting knowledge of brick walls or kung fu, the pixel data that it receives from an Atari game is meaningless. Rather than staring uncomprehendingly at the noise, however, a program like DeepMind’s will start analyzing those pixels—sorting them by color, finding edges and patterns, and gradually developing an ability to recognize complex shapes and the ways in which they fit together."
The best news is that the programme's not very good at Pac-Man because it's rubbish at forward planning. So far.

No comments: