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

Inside Google Brain

wired.com

Post reply on HN
Print view View original

31–40 of 77 posts

Re: Inside Google Brain

#31

Post by daughart »

jfields513 wrote: post #29
ckaygusu wrote: post #8

Earlier quoted context omitted.

If you think human brain is so sophisticated that it can perform its cognitive duties with little data, this is simply wrong. While it is definitely not a simple organic construct, it does get stimulated significantly all the time. See [1] what happens when you cut out this factors. Regarding artificial systems, I think more data is the only way to reach super-performing classifiers. The data you supply doesn't have…

Your first statement here is not true. Humans are excellent at learning from very few or even 1 example. Show a toddler a single image of an elephant and the toddler will generalize perfectly on new examples; show a machine a few thousand images of elephants and it might generalize decently if your machine is really clever. There are very few tasks where machine systems achieve anything resembling human level perform…

That toddler has already processed lots of visual image data, examples of objects, nonliving and living, animals, mammals, etc. Don't you think that constitutes a large, important dataset for the problem of elephant recognition?

Re: Inside Google Brain

#32

Post by woodchuck64 »

Seems inevitable that the company with the world's largest distributed compute engine (estimated at 40 petaflops as of 2012, must be 80 petaflops by now) would eventually get into machine-learning.

Re: Inside Google Brain

#34

Post by valarauca1 »

daughart wrote: post #31
jfields513 wrote: post #29

Earlier quoted context omitted.

Your first statement here is not true. Humans are excellent at learning from very few or even 1 example. Show a toddler a single image of an elephant and the toddler will generalize perfectly on new examples; show a machine a few thousand images of elephants and it might generalize decently if your machine is really clever. There are very few tasks where machine systems achieve anything resembling human level perform…

That toddler has already processed lots of visual image data, examples of objects, nonliving and living, animals, mammals, etc. Don't you think that constitutes a large, important dataset for the problem of elephant recognition?

It does but it's unsorted.then post processed.

If you show a child 1000 images or animals. Then show different photographs of animals. And tell the child what animal each animal photograph is, you can now go back to the original 1000 and the explained ones will likely be recognized dispute them never beig initially sorted, or modeled as such.

Going from 5-10 to 1,000,000 is what computers have a problem with. They go from 1,000 to 1,000,000 easily, or even million to billions.

Re: Inside Google Brain

#35

Post by sp332 »

astazangasta wrote: post #27
deong wrote: post #15

Earlier quoted context omitted.

Considering that for the preceding 25 years or so, progress in the state of the art had been annual reductions of far less than 1%, it's a pretty big deal.

From an academic perspective, maybe. In terms of practical use of machine methods, not much. Machine learning is largely hype. I pity the army of PhDs they must have building training sets.

Have you tried Google's voice recognition? It's been fantastic for me.

Re: Inside Google Brain

#36

Post by trevorstrohman »

valarauca1 wrote: post #34
daughart wrote: post #31

Earlier quoted context omitted.

That toddler has already processed lots of visual image data, examples of objects, nonliving and living, animals, mammals, etc. Don't you think that constitutes a large, important dataset for the problem of elephant recognition?

It does but it's unsorted.then post processed. If you show a child 1000 images or animals. Then show different photographs of animals. And tell the child what animal each animal photograph is, you can now go back to the original 1000 and the explained ones will likely be recognized dispute them never beig initially sorted, or modeled as such. Going from 5-10 to 1,000,000 is what computers have a problem with. They go…

You're describing unsupervised training. It works with computers too, as in this article on using Google Brain to build an unsupervised image classifier. http://www.wired.com/2012/06/google-x-neural-network

Re: Inside Google Brain

#37

Post by api »

"Google isn't really a search company-- it's a machine learning company."

No, it's an advertising company. That's who pays the bills. At the end of the day all this cool tech is to better understand and model human beings in order to better push ads.

Sometimes it depresses me that so many of the world's most brilliant minds are working on that, but a generation or two ago they'd all be building doomsday bombs. I guess that's some progress.

Re: Inside Google Brain

#38

Post by penguat »

cliveowen wrote: post #17
jakek wrote: post #9

Earlier quoted context omitted.

https://static.googleusercontent.com/media/research.google.c...

Doesn't this further prove my point? If you're saying that some tasks, like NLP, are too complex to tame and you should just throw more data at it, you're basically capitulating to complexity and taking the easier route. Isn't that the opposite of what researchers should be doing?

There's no shame in taking a non-optimal path, and then working out how to get better at it later. Research is about solving problems, answering questions. Why should that have to be the hard way?

Re: Inside Google Brain

#39

Post by mathattack »

cliveowen wrote: post #5

"They’ve also found that the models tend to become more accurate the more data they consume. That may be the next big goal for Google: building AI models that are based on billions of data points, not just millions. " I'm not versed in machine learning, but it looks to me that any model whose output quality is dependent on the quantity of data it ingests is deeply flawed. There's no doubt a bigger number of samples w…

It would be great to handle problems with only a little data, but more is better is generally true. Also, the goal can be to calibrate the model with a lot of data, and then have it operate on small amounts of data.

Re: Inside Google Brain

#40

Post by dm2 »

api wrote: post #37

"Google isn't really a search company-- it's a machine learning company." No, it's an advertising company. That's who pays the bills. At the end of the day all this cool tech is to better understand and model human beings in order to better push ads. Sometimes it depresses me that so many of the world's most brilliant minds are working on that, but a generation or two ago they'd all be building doomsday bombs. I gues…

If there was anything else they could do that was profitable then they would. Do you have any suggestions?

The only reason Apple has as much money as it does is because it greatly overcharges customers, doesn't participate in research that benefits society, and takes advantage of it's customers psychological need to have the latest model (even if the improvements are minimal).

Post reply on HN