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

TensorFlow: open-source library for machine intelligence

tensorflow.org

Post reply on HN
Print view View original

161–170 of 211 posts

Re: TensorFlow: open-source library for machine intelligence

#161

Post by jheriko »

zer0nes wrote: post #128
jheriko wrote: post #70

i really wish people would stop calling multidimensional arrays tensors. there is already well defined language for this. multidimensional array is fine, psuedotensor is fine. tensor is confusing if you have any previous background with tensor calculus before the word became machine learning flavour of the month. still. this does look pretty cool overall. processing large volumes of data is becoming increasingly less…

Tensor is a much better term than multidimensional array: - It's not as verbose - The concept of tensor has linear algebra operations associated with it while multidimensional array is just a programming term without any attached Math operations.

true, and pseudotensor can be a mouthful too, but its still confusing.

Re: TensorFlow: open-source library for machine intelligence

#162

Post by jheriko »

an4rchy wrote: post #76

I tried going through the site and also the comments but couldn't wrap my head around what this library actually is. It sounds awesome based on the response/comments. Can anyone explain this to a layman?

it enables you to do lots of maths in parallel in a pretty scalable way.

Re: TensorFlow: open-source library for machine intelligence

#164

Post by dharma1 »

varelse wrote: post #54
andyjohnson0 wrote: post #26

"TensorFlow is an Open Source Software Library for Machine Intelligence" and then later "TensorFlow™ is an open source software library for numerical computation using data flow graphs." So it seems to be a dataflow computation library that is being used for AI/learning. Since I know almost nothing about either, I'm wondering if this (dataflow) approach has other applications unrelated to deep learning. Any comments?…

FPGAs are not measuring up to GPUs yet for these tasks. There's too much floating-point math (and yes, Altera is addressing this) for forward prediction, and way too much intermediate state to save for training (GPU memory controllers are 'da bomb for this). Finally, OpenCL compilation time on FPGAs is measured in hours as compared to seconds for GPUs. That said, address all of the above and maybe NVIDIA's stock won'…

did you see this?

http://arxiv.org/pdf/1510.03009v1.pdf

Re: TensorFlow: open-source library for machine intelligence

#165

Post by nickpsecurity »

tomatioaz wrote: post #57
kragen wrote: post #8

This is really significant. At this moment in history, the growth of computer power has made a bunch of important signal-processing and statistical tasks just feasible, so we are seeing things like self-driving cars, superhuman image recognition, and so on. But it's been very difficult to take advantage of the available computational power, because it's in the form of GPUs and clusters. TensorFlow is a library design…

What is Nile? I can't find it on Google.

It was also built with OMeta:

http://www.tinlizzie.org/ometa/

https://en.wikipedia.org/wiki/OMeta

That tool can be used to solve a lot more problems. REBOL/Red and Racket are also taking DSL approach.

Re: TensorFlow: open-source library for machine intelligence

#166

Post by nickpsecurity »

dharma1 wrote: post #164
varelse wrote: post #54

Earlier quoted context omitted.

FPGAs are not measuring up to GPUs yet for these tasks. There's too much floating-point math (and yes, Altera is addressing this) for forward prediction, and way too much intermediate state to save for training (GPU memory controllers are 'da bomb for this). Finally, OpenCL compilation time on FPGAs is measured in hours as compared to seconds for GPUs. That said, address all of the above and maybe NVIDIA's stock won'…

did you see this? http://arxiv.org/pdf/1510.03009v1.pdf

Now THAT has some potential. Both for FPGA's and SIMD/MIMD architectures. Thanks for the link.

Re: TensorFlow: open-source library for machine intelligence

#167

Post by dchichkov »

mtw wrote: post #40
kragen wrote: post #8

This is really significant. At this moment in history, the growth of computer power has made a bunch of important signal-processing and statistical tasks just feasible, so we are seeing things like self-driving cars, superhuman image recognition, and so on. But it's been very difficult to take advantage of the available computational power, because it's in the form of GPUs and clusters. TensorFlow is a library design…

What about Torch or Theano which allow you to use multiple GPUs and clusters? they also have a wide array of libraries which allows you to extend capabilities (itorch etc.). torch is also very fast, most parts written in C so I don't know if Tensorflow would be really that fast compared to existing librairies. One thing find I found interesting is the ability to use the software you designed in research directly in p…

As a side note, it feels like the front page picture of interactive computational graph is a bit misleading - looks like the interface is still using Python (or C++), not fancy GUI... But yes, it looks very similar to a great tool from Yoshua Bengio's group - Theano. So, great! Another amazing tool to take away the grind of doing ML projects!

Re: TensorFlow: open-source library for machine intelligence

#168

Post by Sanddancer »

varelse wrote: post #54
andyjohnson0 wrote: post #26

"TensorFlow is an Open Source Software Library for Machine Intelligence" and then later "TensorFlow™ is an open source software library for numerical computation using data flow graphs." So it seems to be a dataflow computation library that is being used for AI/learning. Since I know almost nothing about either, I'm wondering if this (dataflow) approach has other applications unrelated to deep learning. Any comments?…

FPGAs are not measuring up to GPUs yet for these tasks. There's too much floating-point math (and yes, Altera is addressing this) for forward prediction, and way too much intermediate state to save for training (GPU memory controllers are 'da bomb for this). Finally, OpenCL compilation time on FPGAs is measured in hours as compared to seconds for GPUs. That said, address all of the above and maybe NVIDIA's stock won'…

There are a few people that seem to be working with integer-based deep learning and FPGAs, and even though they're at the beginning of research, things are looking pretty promising. Here's a paper that was released earlier this year that seems to show that at least some algorithms can see a big benefit from FPGAs http://arxiv.org/pdf/1502.02551v1.pdf .

Re: TensorFlow: open-source library for machine intelligence

#169

Post by nickpsecurity »

albertzeyer wrote: post #24
dryginmartini wrote: post #16

How does TensorFlow compare to Torch7 ( http://torch.ch )? They look very similar to me.

Actually, this looks much more like Theano to me. It's all symbolic, it has symbolic differentiation, it's Python and it even seems to have a similar API like Theano. In the Whitepaper ( http://download.tensorflow.org/paper/whitepaper2015.pdf ), it's compared to Theano, Torch and others.

That might be a strong advantage in its favor, though. Building a better version of a proven concept with similar usage/API's often gets more market uptake. Might get more use.

Re: TensorFlow: open-source library for machine intelligence

#170

Post by Sanddancer »

aconz2 wrote: post #27
sudhirj wrote: post #15

Earlier quoted context omitted.

There's a note on the site about being able to move computation to a process on a different machine, but it does mention copying the model. If I understand correctly, I think models tend to be quite small, though. Does it actually make sense to train a model simultaneously on different machines? I can understand running the same model on lots of machines, of course.

I was interested in whether the license only permits a single machine.

Nope, nothing in the license prohibiting it. Seems more a case that they just haven't released the glue for it to run on multiple machines, but hope to have it added one way or another.
Post reply on HN