The Future of Deep Learning Is Here

This approach of trying to make sense of causality and time and space does remind me of earlier efforts to build artificial intelligence. The techniques that we had in the sixties and seventies really weren't set up for that. And so they weren't very good at representing things that are kind of statistically true, but not a hundred % trute. There were weaknesses in the specific techniques. But i think the other thing i would say is that it's a totally unfair comparison. Deep learning was terrible in the nine fifties, it was useless. It took knows 60 years before it was actually useful. To see the full you need to upgrat a net sweet bit oracle head to