Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Building high-level features using large scale unsupervised learning

research.google.com

Post reply on HN
Print view View original

51–60 of 196 posts

Re: Building high-level features using large scale unsupervised learning

#51

Post by chmike »

The only originality in this work is the processing power used. The principle in it self is not original.

For a possible resemblance with the real cortical neural network working principle and face or object recognition, this is just a farce.

Regarding getting closer to the presumed singularity, this is like saying that cutting flint is close to making diamonds.

The authors didn't claim that, but the abusive use of "neural network" for such kinds of applications is just doing that. It is a dishonest abuse of people who can't make the difference.

The true problem is that significant quality work toward modeling real cortical neural network is drown in the sea of such faker crap.

Re: Building high-level features using large scale unsupervised learning

#52

Post by Devilboy »

sown wrote: post #41

I'm seriously considering quitting my job and studying ML for a few months in a desperate attempt to get work in projects like this. I feel like I'm missing out but too dumb for traditional grad school.

Have you seen the online courses?

https://www.coursera.org/course/ml (From one of the authors of this paper!)

https://www.coursera.org/course/vision

https://www.coursera.org/course/computervision

Prof. Hinton's videos are very watchable:

http://www.youtube.com/watch?v=AyzOUbkUf3M

http://www.youtube.com/watch?v=VdIURAu1-aU

Re: Building high-level features using large scale unsupervised learning

#53

Post by Homunculiheaded »

There was an interesting discussion on Quora about this recently[0]

The most relevant quote being perhaps:

"The magic of the brain is not the number of neurons, but how the circuits are wired and how they function dynamically. If you put 1 billion transistors together, you don't get a functioning CPU. And if you put 100 billion neurons together, you don't get an intelligent brain."

0. http://www.quora.com/How-big-is-the-largest-feedforward-neur...

Re: Building high-level features using large scale unsupervised learning

#54

Post by marcusrobbins »

tansey wrote: post #28
marshallp wrote: post #12

Earlier quoted context omitted.

It does this for 20,000 different objects categories - this is getting close to matching human visual ability (and there are huge societal implications if computer reach that standard). This is the most powerful AI experiment yet conducted (publicly known).

> It does this for 20,000 different objects categories With 15.8% accuracy. > This is the most powerful AI experiment yet conducted (publicly known). It's only powerful because they threw more cores at it than anyone else has previously attempted. From a quick skimming of the paper, there does not appear to be a lot of novel algorithmic contribution here. It's the same basic autoencoder that Hinton proposed years ago…

I think this is the most important aspect of this paper. Throwing more computing power at the problem increases performance significantly. It is possible that our algorithms are adequate but our hardware is not.

Re: Building high-level features using large scale unsupervised learning

#55

Post by _delirium »

chmike wrote: post #51

The only originality in this work is the processing power used. The principle in it self is not original. For a possible resemblance with the real cortical neural network working principle and face or object recognition, this is just a farce. Regarding getting closer to the presumed singularity, this is like saying that cutting flint is close to making diamonds. The authors didn't claim that, but the abusive use of "…

I think much of this is overhyped as well, but I disagree that whether modeling human brain structure is relevant. The term "neural network" has historical baggage (responsible for some of the hype), but these days refers to a class of mathematical approaches with only historical connection to "neurons". Those can be interesting on their own for AI purposes, and imo accurate modeling of the human brian, while interesting for neuroscience research, is not necessarily the way forward for AI research.

Re: Building high-level features using large scale unsupervised learning

#56

Post by roel_v »

heretohelp wrote: post #18
marshallp wrote: post #14

Earlier quoted context omitted.

They just have to scale it up - more computers, more days, and the accuracy level should increase accordingly (that is my intuition and hope on this, though i could be wrong).

Haha, no. --- last company was in computer vision.

"last company was in computer vision."

Did you sell, leave or did it fail? Why? I have some ideas that I think are novel applications of computer vision, and just within the range of what's feasible, but it seems that most computer vision applications look like that at first, and then after 90% done find out that the second 90% is exponentially harder and, realistically, infeasible. How could I test my ideas against that? Or am I asking from wrong premises?

Re: Building high-level features using large scale unsupervised learning

#57

Post by yaroslavvb »

jpeterson wrote: post #5

Maybe I'm missing something here, but how exactly is it "unlabeled" data if they're specifically feeding it millions of pictures of "faces"? I mean, if you make a specific selection of the type of images you train the network on, isn't that basically equivalent to labeling them?

They are feeding 10M frames from random YouTube videos, 1 frame per video. Only 3% of 60x60 patches from those frames contained faces
Post reply on HN