Humans are still much better than computers at recognizing speech. — Geoffrey Hinton Copy Share Image
My main interest is in trying to find radically different kinds of neural nets. — Geoffrey Hinton Copy Share Image
Early AI was mainly based on logic. You're trying to make computers that reason like people. The second route is from biology:… — Geoffrey Hinton Copy Share Image
The question is, can we make neural networks that are 1,000 times bigger? And how can we do that with existing computation? — Geoffrey Hinton Copy Share Image
I think we should think of AI as the intellectual equivalent of a backhoe. It will be much better than us at… — Geoffrey Hinton Copy Share Image
Once your computer is pretending to be a neural net, you get it to be able to do a particular task by… — Geoffrey Hinton Copy Share Image
All you need is lots and lots of data and lots of information about what the right answer is, and you'll be… — Geoffrey Hinton Copy Share Image
The pooling operation used in convolutional neural networks is a big mistake, and the fact that it works so well is a… — Geoffrey Hinton Copy Share Image
The paradigm for intelligence was logical reasoning, and the idea of what an internal representation would look like was it would be… — Geoffrey Hinton Copy Share Image
Any new technology, if it's used by evil people, bad things can happen. But that's more a question of the politics of… — Geoffrey Hinton Copy Share Image
I think people need to understand that deep learning is making a lot of things, behind-the-scenes, much better. Deep learning is already… — Geoffrey Hinton Copy Share Image
Most people in AI, particularly the younger ones, now believe that if you want a system that has a lot of knowledge… — Geoffrey Hinton Copy Share Image
I have always been convinced that the only way to get artificial intelligence to work is to do the computation in a… — Geoffrey Hinton Copy Share Image
Now that neural nets work, industry and government have started calling neural nets AI. And the people in AI who spent all… — Geoffrey Hinton Copy Share Image
Deep learning is already working in Google search and in image search; it allows you to image-search a term like 'hug.' It's… — Geoffrey Hinton Copy Share Image
Everybody right now, they look at the current technology, and they think, 'OK, that's what artificial neural nets are.' And they don't… — Geoffrey Hinton Copy Share Image
As soon as you have good mechanical technology, you can make things like backhoes that can dig holes in the road. But… — Geoffrey Hinton Copy Share Image
We now think of internal representation as great big vectors, and we do not think of logic as the paradigm for how… — Geoffrey Hinton Copy Share Image
My view is we should be doing everything we can to come up with ways of exploiting the current technology effectively. — Geoffrey Hinton Copy Share Image
I am scared that if you make the technology work better, you help the NSA misuse it more. I'd be more worried… — Geoffrey Hinton Copy Share Image
Take any old classification problem where you have a lot of data, and it's going to be solved by deep learning. There's… — Geoffrey Hinton Copy Share Image
In deep learning, the algorithms we use now are versions of the algorithms we were developing in the 1980s, the 1990s. People… — Geoffrey Hinton Copy Share Image
Irony is going to be hard to get. You have to be master of the literal first. But then, Americans don't get irony either.… — Geoffrey Hinton Copy Share
My main interest is in trying to find radically different kinds of neural nets. — Geoffrey Hinton Copy Share
We want to take AI and CIFAR to wonderful new places, where no person, no student, no program has gone before. — Geoffrey Hinton Copy Share
In deep learning, the algorithms we use now are versions of the algorithms we were developing in the 1980s, the 1990s. People were very… — Geoffrey Hinton Copy Share
The role of radiologists will evolve from doing perceptual things that could probably be done by a highly trained pigeon to doing far more… — Geoffrey Hinton Copy Share
I get very excited when we discover a way of making neural networks better - and when that's closely related to how the brain… — Geoffrey Hinton Copy Share
Deep learning is already working in Google search and in image search; it allows you to image-search a term like 'hug.' It's used to… — Geoffrey Hinton Copy Share
In A.I., the holy grail was how do you generate internal representations. — Geoffrey Hinton Copy Share
As soon as you have good mechanical technology, you can make things like backhoes that can dig holes in the road. But of course… — Geoffrey Hinton Copy Share
To deal with a 14-dimensional space, visualize a 3-D space and say 'fourteen' to yourself very loudly. Everyone does it. — Geoffrey Hinton Copy Share
In science, you can say things that seem crazy, but in the long run, they can turn out to be right. We can get… — Geoffrey Hinton Copy Share
My view is we should be doing everything we can to come up with ways of exploiting the current technology effectively. — Geoffrey Hinton Copy Share
