The Next Generation of Neural Networks
Posted by on 20th, 2009
Google Tech Talks November, 29 2007 In the 1980’s, new learning algorithms for neural networks promised to solve difficult classification tasks, like speech or object recognition, by learning many layers of non-linear features. The results were disappointing for two reasons: There was never enough labeled data to learn millions of complicated features and the learning was much too slow in deep neural networks with many layers of features. These problems can now be overcome by learning one …
In 22:00, After presenting some number to the neural network. Shouldnt shouldnt it change the weights so the data matches more to one number, and when it runs backwards, why does it change it weights ?
December 12th, 2009 at 3:27 pm
Interesting!
//K
December 12th, 2009 at 3:27 pm
Who cares?The only thing that matters is what he is saying, which is fascinating (if not entirely novel). If he wants to make a few gentle jokes to leaven things, more power to him.
December 12th, 2009 at 3:27 pm
It makes sense from a programming stand point, but still does not offer true A.I.
December 12th, 2009 at 3:27 pm
36:20 lol @ the 30-dimensional supermarket
December 12th, 2009 at 3:27 pm
you are right…. getting politically in a lecture/presentation of computer science is imo very unprofessional.
December 12th, 2009 at 3:27 pm
you guys are all idiots
December 12th, 2009 at 3:27 pm
it was a good talk until he got all political
what a fag
December 12th, 2009 at 3:27 pm
Nice work. keep it up. mean time come for social media marketing for esteembpo**com
December 12th, 2009 at 3:27 pm
Nice work. keep it up. mean time come for social media marketing for esteembpo**com
December 12th, 2009 at 3:27 pm
Nice try. Keep it up check out esteembpo + com for social media marketing. erfdsf
December 12th, 2009 at 3:27 pm
Nice try. Keep it up check out esteembpo + com for social media marketing. rtyhfgh
December 12th, 2009 at 3:27 pm
“Yann LeCun (& Bottou) and can make it work or more or less anything”… haha nice one… :)..
December 12th, 2009 at 3:27 pm
Thanks… backs up the way that I thought about it.
December 12th, 2009 at 3:27 pm
Say you have three pictures, one is a rotten apple, one is a healthy apple, and an orange. You want to train to detect between apples and oranges. Without knowing which is which, it is difficult. Giving the hint (i.e. label) that the first two are apples, the program can learn much easier.
December 12th, 2009 at 3:27 pm
Can someone explain the concept of labeled and unlabeled data? Perhaps an example would be the best way to go.
December 12th, 2009 at 3:27 pm
Jeff Hawkins spent half his talk restating his question of why the lack of brain theory? Studying the physical brain is a young subject as concrete neuroscience has birthed within the past century; therefore there is little theory to accompany it.
December 12th, 2009 at 3:27 pm