The Next Generation of Neural Networks

alanjlockett Says:

Dec 6, 2008 - It sounds like most of the people posting comments have no idea who Geoff Hinton is. The guy is probably the most prominent figure in neural net research since 1984. He was part of developing backpropagation, Restricted Boltzmann Machines, Deep Belief Nets, Contrastive Divergence learning, etc. There are other very important approaches to neural nets, but Hinton's are the best known. Jeff Hawkins, by comparison, is a layman. He has very interesting ideas, and he may be right, but he is vague.

alanjlockett Says:

Dec 6, 2008 - The problem with fully interconnected networks is that there is no known way to train them. You get better results by segmenting the network into layers that place limits on the connectivity. Boltzmann machines are completely interconnected with undirected links. But it was slow and impractical to train networks of any size. Neuroevolution is another group of techniques for training fully connected recurrent nets, but it hasn't had great success with large networks (whereas DBNs can be large)

lilysleighpetal Says:

Dec 7, 2008 - 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.

napone0 Says:

Dec 24, 2008 - I'm working on a power neural net using R that forecasts scrap prices (which are very difficult to forecast). So far, I've had success with directional accuracy using just autoregressive inputs. If anyone has any additional ideas for inputs, let me know.

dings1337 Says:

Jan 13, 2009 - Great tech video. My favourite currently. I didn't understand everything in detail, but it's really fascinating how it works and what can be done with it. I need to get into this and play with it myself.

OriginalAtomicSheep Says:

Feb 19, 2009 - Can someone explain the concept of labeled and unlabeled data? Perhaps an example would be the best way to go.

teclis1 Says:

Feb 25, 2009 - 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.

OriginalAtomicSheep Says:

Mar 2, 2009 - Thanks... backs up the way that I thought about it.

fcycles Says:

Mar 19, 2009 - very nice and interesting demontration. I got one question about it. During the reconstruction demontration in which a number is being fix and we see the neuron network activities and the resulting image. The number 5 was quite nice and then a 6 appear. He say that it's still in process to show up 5... but, I wonder what kind of effect this will create on a bigger data set?

faunflynn Says:

Apr 5, 2009 - Some one has to go through all the data and label it by hand. The labels are what is learned. Labeling the data takes forever. I'm never ever doing it again.

nirvana4ol Says:

Jun 9, 2009 - "Yann LeCun ( Bottou) and can make it work or more or less anything"... haha nice one... :)..

KraigPierson Says:

Jun 12, 2009 - Nice try. Keep it up check out esteembpo + com for social media marketing. rtyhfgh

DoloresTripp Says:

Jun 13, 2009 - Nice try. Keep it up check out esteembpo + com for social media marketing. erfdsf

lawerenceburch Says:

Jun 15, 2009 - Nice work. keep it up. mean time come for social media marketing for esteembpo**com

titalminarisa Says:

Jun 15, 2009 - Nice work. keep it up. mean time come for social media marketing for esteembpo**com

clustro Says:

Jun 27, 2009 - it was a good talk until he got all political what a fag

Malicorian Says:

Jun 30, 2009 - you guys are all idiots

McYxee Says:

Jul 1, 2009 - you are right.... getting politically in a lecture/presentation of computer science is imo very unprofessional.

UnowMe00 Says:

Jul 8, 2009 - lol, great talk! the jokes are ok, he is self-ironical also... I love the idea with the random noise on ravines to form abstractions of perception and reversely generation! It's simply elegant...

blablablag Says:

Jul 10, 2009 - 36:20 lol @ the 30-dimensional supermarket :D

MrNeo2001 Says:

Jul 16, 2009 - It makes sense from a programming stand point, but still does not offer true A.I.

mallardvasey Says:

Aug 10, 2009 - 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.

Destruktor6666 Says:

Aug 24, 2009 - THAT is what confuses you! Really?! I don't know what is more useless: your asinine post or this pointless response.

kilianguntner Says:

Sep 13, 2009 - Interesting! :) //K

shorty0802 Says:

Sep 20, 2009 - 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 ?