A Quote by Geoffrey Hinton
The pooling operation used in convolutional neural networks is a big mistake, and the fact that it works so well is a disaster.
Related Quotes
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.
I get very excited when we discover a way of making neural networks better - and when that's closely related to how the brain works.
The big 3 networks don't like the fact that there's a Rush Limbaugh out there, they don't like the fact that there's a Fox News, they don't like the fact that there's a Matt Drudge. They liked it when it was nice, when it was just the three of them. Well, it ain't that way anymore.
Obamacare is a disaster. If you look at even Canada, the people come down. When they want an operation, they come to the United States to get the operation. You look at what's going on. It is a disaster in terms of cost, of course.
Health care - the ability of neural networks to ingest lots of data and make predictions is very well suited to this area, and potentially will have a huge societal impact.
The continuous networks of neural circuitry accomplish their functions using multiple, independently discovered strategies. The brain lends itself well to the complexity of the world, but poorly to clear-cut cartography.
Emotions are enmeshed in the neural networks of reason.
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.
The question is, can we make neural networks that are 1,000 times bigger? And how can we do that with existing computation?
Deep neural networks are responsible for some of the greatest advances in modern computer science.
One of the real dilemmas we have in our country and around the world is that what works in politics is organization and conflict. That is, drawing the sharp distinctions. But in real life, what works is networks and cooperation. And we need victories in real life, so we've got to get back to networks and cooperation, not just conflict. But politics has always been about conflict, and in the coverage of politics, information dissemination tends to be organized around conflict as well.
When you study, as I did, every theatrical beginning in this country, none of them have been greeted well. The Royal Shakespeare Company was a disaster, Peter Hall was a disaster, Richard Eyre was a disaster, Trevor Nunn was always a disaster.
There are neural networks that can build whole apps from scratch - so why are we teaching high school kids to code?
Operation Fast and Furious was flawed in concept and flawed in execution. The tactics used in this operation violate Department of Justice policy and should never have been used.
Drama is based on the Mistake. I think someone is my friend when he really is my enemy, that I am free to marry a woman when in fact she is my mother, that this person is a chambermaid when it is a young nobleman in disguise, that this well-dressed young man is rich when he is really a penniless adventurer, or that if I do this such and such a result will follow when in fact it results in something very different. All good drama has two movements, first the making of the mistake, then the discovery that it was a mistake.
My particular focus at the moment is on the development of genetic algorithms and neural networks that work together to create computer architectural systems.
Related Authors
Abraham Maslow Quotes
American
Psychologist
Carl Jung Quotes
Swiss
Psychologist
Daniel Kahneman Quotes
Israeli
Psychologist
Edward de Bono Quotes
English
Psychologist
Erich Fromm Quotes
American
Psychologist
James Hillman Quotes
American
Psychologist
M. Scott Peck Quotes
American
Psychologist
Mihaly Csikszentmihalyi Quotes
Hungarian
Psychologist
Nathaniel Branden Quotes
American
Psychologist
Ram Dass Quotes
American
Psychologist
Rollo May Quotes
American
Psychologist
Sigmund Freud Quotes
Austrian
Psychologist
Tara Brach Quotes
American
Psychologist
Viktor E. Frankl Quotes
Austrian
Psychologist
Wayne Dyer Quotes
American
Psychologist