A Quote by Geoffrey Hinton

My main interest is in trying to find radically different kinds of neural nets. — © Geoffrey Hinton
My main interest is in trying to find radically different kinds of neural nets.
Now that neural nets work, industry and government have started calling neural nets AI. And the people in AI who spent all their life mocking neural nets and saying they'd never do anything are now happy to call them AI and try and get some of the money.
The kinds of nets we know how to weave determine the kinds of nets we cast. These nets, in turn, determine the kinds of fish we catch.
New methods always look better than old ones. Neural nets are better than logistic regression, support vector machines are better than neural nets, etc.
The first attempts to consider the behavior of so-called "random neural nets" in a systematic way have led to a series of problems concerned with relations between the "structure" and the "function" of such nets. The "structure" of a random net is not a clearly defined topological manifold such as could be used to describe a circuit with explicitly given connections. In a random neural net, one does not speak of "this" neuron synapsing on "that" one, but rather in terms of tendencies and probabilities associated with points or regions in the net.
The important thing to know about playing to win and playing not to lose is that there are actually different neural networks that are being used. It's not very easy to do both at the same time and, if you are trying to have a playing to win mentality, you're going for it, there's some things that trip you up or trigger the wrong neural network. If you start worrying about your mistakes all of a sudden, if you get too focused on the facts and the details, these are going to shift your neural networks and sort of screw up your strategy.
Having been trained as a computer scientist in the '90s, everybody knew that AI didn't work. People tried it. They tried neural nets, and none of it worked.
The paradigm for intelligence was logical reasoning, and the idea of what an internal representation would look like was it would be some kind of symbolic structure. That has completely changed with these big neural nets.
One can, in principle, outline sort of a set of neural circuits that are critically involved and even identify disorders that affect different components of that neural circuit and see what happens if you knock out, for example, inability to recognize faces, how it affects your response to portraiture.
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.
I've been really fortunate to be able to do different kinds of films in different scales, different genres, different kinds of roles, and that is important to me.
What is more important today for the audience is to have different kinds of content. They like variety, they like different kinds of stories, different kinds of entertainment.
Everyday something new pops into my mind: I could do this next or I could do that next. I want to grow more and more and show people different sides of myself, whether it's different kinds of music, different kinds of movies, or different kinds of television.
First, we have to find a common vocabulary for energy security. This notion has a radically different meaning for different people. For Americans it is a geopolitical question. For the Europeans right now it is very much focused on the dependence on imported natural gas.
Marriage has a unique place because it speaks of an absolute faithfulness, a covenant between radically different persons, male and female; and so it echoes the absolute covenant of God with his chosen, a covenant between radically different partners.
Characteristically, however, the overthrow of the dictator simply means that there will be another dictator. ... the policies they follow will probably not be radically different. If we look around the world, we quickly realize that these policies will not be radically different from those that would be followed by a democracy either.
It's okay to be kind of looking for what you want and trying out all kinds of different ideas and different course work, etc.
This site uses cookies to ensure you get the best experience. More info...
Got it!