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

How Convolutional Neural Networks Work

brohrer.github.io

Post reply on HN
Print view View original

31–40 of 54 posts

Re: How Convolutional Neural Networks Work

#31

Post by oh_sigh »

viraptor wrote: post #28
lettergram wrote: post #25

Earlier quoted context omitted.

I tried to get it released before, but was shut down by the "open source office". So I can't give you the exact script. However, h2o has a script that launches a cluster, that's very similar: https://github.com/ledell/h2oEnsemble-benchmarks/blob/master... You can also do stuff like following in python to execute some code: os.system("scp script_demo.py " + sys.argv[1] + ":/home/ubuntu/") os.system("ssh " + sys.argv[1…

Even if it may not matter in this case specifically, this is a terrible example. "sudo chmod 777" in public code is basically "I don't know what I'm doing, but go on, do the same thing yourself" :( You don't need sudo, because it's your file. You need just "chmod 755", not "777". And you don't need chmod in the first place - just run "python script_demo.py".

Yes. On the other hand, there isn't a strong overlap with machine learning experts and security experts(I'm sure there will be in coming years though, as security experts start using NNs to detect anomalous/dangerous behavior).

Re: How Convolutional Neural Networks Work

#32

Post by danieltillett »

viraptor wrote: post #28
lettergram wrote: post #25

Earlier quoted context omitted.

I tried to get it released before, but was shut down by the "open source office". So I can't give you the exact script. However, h2o has a script that launches a cluster, that's very similar: https://github.com/ledell/h2oEnsemble-benchmarks/blob/master... You can also do stuff like following in python to execute some code: os.system("scp script_demo.py " + sys.argv[1] + ":/home/ubuntu/") os.system("ssh " + sys.argv[1…

Even if it may not matter in this case specifically, this is a terrible example. "sudo chmod 777" in public code is basically "I don't know what I'm doing, but go on, do the same thing yourself" :( You don't need sudo, because it's your file. You need just "chmod 755", not "777". And you don't need chmod in the first place - just run "python script_demo.py".

These things come about because people learn the simple way to solve all permission problems is just do everything as su (or root) and chmod everything to 777. The problem is it does solve all problems (well sweep them under the rug) - I guess when the only tool you have is a hammer everything looks like a nail.

Re: How Convolutional Neural Networks Work

#33

Post by ionforce »

drewm1980 wrote: post #17

I am supportive of clear explanations of some of the building blocks, but I worry repeatedly describing things as being grade school math level gives the wrong impression about the actual learning curve for getting up to speed on working with CNN's. Yes, the building blocks are easy to understand, but actually understanding why a given network structure, or optimization technique isn't working, is a black art. And if…

It's a better start than having no visibility into the topic at all.

Re: How Convolutional Neural Networks Work

#34

Post by viraptor »

oh_sigh wrote: post #31
viraptor wrote: post #28

Earlier quoted context omitted.

Even if it may not matter in this case specifically, this is a terrible example. "sudo chmod 777" in public code is basically "I don't know what I'm doing, but go on, do the same thing yourself" :( You don't need sudo, because it's your file. You need just "chmod 755", not "777". And you don't need chmod in the first place - just run "python script_demo.py".

Yes. On the other hand, there isn't a strong overlap with machine learning experts and security experts(I'm sure there will be in coming years though, as security experts start using NNs to detect anomalous/dangerous behavior).

I know what you mean, but I disagree with "security experts". You don't need to be a security expert, just know the basics of how privileges work on your system. And if people don't, we just need to keep calling it out, because otherwise code like this ends up in production one day, where it actually matters.

Simpler bash equivalent for the record:

    scp script_demo.py "$1"
    ssh "$1" python script_demo.py
    scp "$1":output/* ./output/

Re: How Convolutional Neural Networks Work

#35

Post by bilbobeer »

MrFeynmannsJoke wrote: post #4

So ist works just like i thought it would. Why are CNN so hyped? Wasnt all this already known decades ago? Or is it just because we can afford the computing power?

In 1965 Cooley-Tukey published their famous FFT paper, funny thing is that at Standard Oil they were using FFT in the 1950's, because it could be used for analyzing 'Russian' atomic bomb seismic signatures in real-time it took some 10+ years before it became public ( openly published ), but it was routine in BIG-OIL in 1950's.

Now jump to CNN, we were doing CNN on Cray's in the 1970's on Seismic 3d data ( acoustic sound waves pressure/sheer ) in order to find oil deposits, its the same stuff I see in CNN algo's of today, and its the exact same stuff we were doing in the 1970's in visualizing seismic data (P-S wave ratios were the color that told you what kind of rock/substance you propagated ).

We used to call this 'around the wheel', I suspect that its good to make the kids think this stuff is all something new, most of the foundation of computational ML was designed in 1950's, hell Von Neuman wrote the book on Cybernetic's, automating the human mind with computers, again 1950's.

Another perspective is given the quality ( poor ) that's being leaked, and given corporate history, I suspect that BIG-OIL, and BIG-NSA of today have stuff that is super good and advanced and most of what they leak to GIT-HUB is just garbage.

In summary keep it simply, learn how it really works, and then dial in your own algorithm, and you too will discover the holy-grail, but remember that edoocation is always 15-20 years lagging industry. It's always been this way, and always will. NSA/CIA has always mandated a competitive edge over the foreign gov's, never assume that anything you get for free, or academia is cutting-edge.

( Lastly George Green developed the Math here, back in 1816-ish, thus the Convolutional in CNN is 200 years old to be exact. )

Re: How Convolutional Neural Networks Work

#36

Post by ClassyJacket »

lettergram wrote: post #25
danieltillett wrote: post #21

Earlier quoted context omitted.

Would you mind sharing this script? I am thinking of investing in the 2K workstation, but this sounds like a much more efficient way to go.

I tried to get it released before, but was shut down by the "open source office". So I can't give you the exact script. However, h2o has a script that launches a cluster, that's very similar: https://github.com/ledell/h2oEnsemble-benchmarks/blob/master... You can also do stuff like following in python to execute some code: os.system("scp script_demo.py " + sys.argv[1] + ":/home/ubuntu/") os.system("ssh " + sys.argv[1…

>but was shut down by the "open source office"

Can you expand on that? What happened?

Re: How Convolutional Neural Networks Work

#37

Post by empath75 »

viraptor wrote: post #28
lettergram wrote: post #25

Earlier quoted context omitted.

I tried to get it released before, but was shut down by the "open source office". So I can't give you the exact script. However, h2o has a script that launches a cluster, that's very similar: https://github.com/ledell/h2oEnsemble-benchmarks/blob/master... You can also do stuff like following in python to execute some code: os.system("scp script_demo.py " + sys.argv[1] + ":/home/ubuntu/") os.system("ssh " + sys.argv[1…

Even if it may not matter in this case specifically, this is a terrible example. "sudo chmod 777" in public code is basically "I don't know what I'm doing, but go on, do the same thing yourself" :( You don't need sudo, because it's your file. You need just "chmod 755", not "777". And you don't need chmod in the first place - just run "python script_demo.py".

If you're launching an AWS instance that doesn't have any ports open and is going to terminate in a few hours, who cares?

Re: How Convolutional Neural Networks Work

#38

Post by viraptor »

empath75 wrote: post #37
viraptor wrote: post #28

Earlier quoted context omitted.

Even if it may not matter in this case specifically, this is a terrible example. "sudo chmod 777" in public code is basically "I don't know what I'm doing, but go on, do the same thing yourself" :( You don't need sudo, because it's your file. You need just "chmod 755", not "777". And you don't need chmod in the first place - just run "python script_demo.py".

If you're launching an AWS instance that doesn't have any ports open and is going to terminate in a few hours, who cares?

As I said: "Even if it may not matter in this case". But what about the next time? (poster obviously doesn't understand the code) What about people who read this comment and follow the advice because it works? (happens all the time with SO) What about when your script becomes the standard deployment method for the company? (happens everywhere) What about people who don't know about file privileges either and blindly copy what they see here?

There's lots of things we do that you could say "who cares?" about. Single letter variables. Comments. Const-correctness. Unnecessary N^2 algorithms. Usually it turns out that either you or someone you work with cares a few months/years afterwards. So just learn to do it correctly the first time. Especially if the correct way takes less time than the "magic fix".

Re: How Convolutional Neural Networks Work

#39

Post by j1vms »

> CNNs can be used to categorize other types of data too. The trick is, whatever data type you start with, to transform it to make it look like an image.

This is an interesting point, and I assume that 'make it look look like an image' means the same thing as 'think of it as an image'. Can others here who works with CNNs regularly or professionally, comment on whether the author's intuition is essentially correct (give or take some details of course)?

Re: How Convolutional Neural Networks Work

#40

Post by anantzoid »

lettergram wrote: post #18
drewm1980 wrote: post #17

I am supportive of clear explanations of some of the building blocks, but I worry repeatedly describing things as being grade school math level gives the wrong impression about the actual learning curve for getting up to speed on working with CNN's. Yes, the building blocks are easy to understand, but actually understanding why a given network structure, or optimization technique isn't working, is a black art. And if…

I setup an automated script to setup a AWS g2 instance, train my neural net using tensorflow, copy my model to my personal computer, and spin down. It costs like $5-$10 to train/test most neural network models. My most expensive model cost like $100 and required a ton of time and resources. It took like 4 days or something. You really dont need $2k workstation.. Of course, for personal use I do have a gtx 1080 becaus…

Spot instances cost way cheaper. The only downside is you need to create an AMI everytime before termination. But, also, AWS g2 has NVIDIA Grid K50 with 4GB memory, so it's not very good with performance.
Post reply on HN