Finally, however, in the last decade ­Hinton and other researchers made some fundamental conceptual breakthroughs. In 2006, Hinton developed a more efficient way to teach individual layers of neurons. The first layer learns primitive features, like an edge in an image or the tiniest unit of speech sound. It does this by finding combinations of digitized pixels or sound waves that occur more often than they should by chance. Once that layer accurately recognizes those features, they’re fed to the next layer, which trains itself to recognize more complex features, like a corner or a combination of speech sounds. The process is repeated in successive layers until the system can reliably recognize phonemes or objects.

via New Techniques from Google and Ray Kurzweil Are Taking Artificial Intelligence to Another Level | MIT Technology Review.

Nitin Badjatia

Nitin Badjatia

Nearly thirty years inside financial markets and enterprise software. He writes here about how AI is rewriting the way companies work, and where the value ends up.

About →    Get in touch →

Or join the conversation on LinkedIn →

More writing

All writing →

Catch the next idea while it’s still early.

Subscribe →