Geoffrey Hinton Quotes

The neural network is this kind of technology that is not an algorithm, it is a network that has weights on it, and you can adjust the weights so that it learns. You teach it through trials.

As commentators like the American psychologist Gary Marcus have noted, it's extremely difficult to teach a computer to recognise cats. And that's not for want of trying.

The thing that's going to make artificial intelligence so powerful is its ability to learn, and the way AI learns is to look at human culture.

I think the first wave of deep learning progress was mainly big companies with a ton of data training very large neural networks, right? So if you want to build a speech recognition system, train it on 100,000 hours of data.

When you have a large amount of data that is labeled so a computer knows what it means, and you have a large amount of computing power, and you're trying to find patterns in that data, we've found that deep learning is unbeatable.

Take any old classification problem where you have a lot of data, and it's going to be solved by deep learning. There's going to be thousands of applications of deep learning.

All you need is lots and lots of data and lots of information about what the right answer is, and you'll be able to train a big neural net to do what you want.

Pretend I asked, now answer the question.

Graphics has lately made a great shift towards machine learning, which itself is about understanding data.

Mimicking the intricacies of the human brain, a neuro-inspired computer would work in a fashion similar to the way neurons and synapses communicate. It could potentially learn or develop memory.

Data is going to be dynamic... and, combined with the performance of computing that allows for artificial intelligence to be applied, is going to bring all kinds of insights and additives to enhance everyday life.

Computer vision and machine learning have really started to take off, but for most people, the whole idea of what is a computer seeing when it's looking at an image is relatively obscure.

Machine learning is the science of getting computers to learn without being explicitly programmed.

Humans are unbelievably data efficient. You don't have to drive 1 million miles to drive a car, but the way we teach a self-driving car is have it drive a million miles.

None of us today know how to get computers to learn with the speed and flexibility of a child.

The deep learning techniques, while relatively easy to learn, are quite foreign to traditional engineering modalities. It takes a different mindset and a relaxation of the presumption of control. The practitioners are like magi, sequestered from the rest of a typical engineering process.

Want to train a machine translation system? Train it on a gazillion pairs of sentences of parallel corpora, and that creates a lot of breakthrough results. Increasingly, I'm seeing results on small data where you want to try to take in results even if you have 1,000 images.

The revolution in deep nets has been very profound. It definitely surprised me, even though I was sitting right there.

Most of the value of deep learning today is in narrow domains where you can get a lot of data. Here's one example of something it cannot do: have a meaningful conversation.

You could claim that moving from pixelated perception, where the robot looks at sensor data, to understanding and predicting the environment is a Holy Grail of artificial intelligence.

With the Google Brain project, we made the decision to build deep learning processes on top of Google's existing infrastructure.

In A.I., the holy grail was how do you generate internal representations.

The challenge for what everybody's seeing in deep learning - the software richness is really quite high. In training, you have to wait days and weeks before it comes back to tell you whether your model works or not. And in the beginning, they all don't work.

Everybody right now, they look at the current technology, and they think, 'OK, that's what artificial neural nets are.' And they don't realize how arbitrary it is. We just made it up! And there's no reason why we shouldn't make up something else.

Understanding vision and building visual systems is really understanding intelligence.