Mathematicians have struggled to understand why deep learning techniques work. This is important because these techniques underpin many of the recent breakthroughs in artificial intelligence including Deep Mind's recent Go victory.
New research by Henry Lin at Harvard and Max Tegmark at MIT shows that it is physics and the nature of the universe that provides the answer. This improved understanding of why should underpin even faster progress in the future. Given how important artificial intelligence is becoming, this has profound implications across many industries.
Deep learning techniques have transformed the world of artificial intelligence. One by one, the abilities and techniques that humans once imagined were uniquely our own have begun to fall to the onslaught of ever more powerful machines. Deep neural networks are now better than humans at tasks such as face recognition and object recognition. They’ve mastered the ancient game of Go and thrashed the best human players. But there is a problem. There is no mathematical reason why networks arranged in layers should be so good at these challenges. Today that changes thanks to the work of Henry Lin and Max Tegmark. These guys say the reason why mathematicians have been so embarrassed is that the answer depends on the nature of the universe. In other words, the answer lies in the regime of physics rather than mathematics.