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

151–160 of 211 posts

Re: TensorFlow: open-source library for machine intelligence

#151

Post by mjw »

pathsjs wrote: post #47
vegabook wrote: post #12

Earlier quoted context omitted.

I am really excited about this library. Tensors are the future; matrices are going to look so old in a few years. In fairness, Theano already knew that. I cannot wait to dig into this and am very relieved that Google's best are still using Python for this endeavour...but...using Python 2.7. I have just recently been persuaded by the community that 3.5 is cost free, and here I have this enormous counterexample. For th…

> Tensors are the future; matrices are going to look so old in a few years. I am honestly curious about this point of view. Is there any example where actual multidimensional tensor have any relevance? What I mostly see around is just standard linear algebra operations on matrices and vectors lifted to higher-dimensional tensors point-wise (for instance applying a certain operation to all 2-dimensional subtensors of…

> What I mostly see around is just standard linear algebra operations on matrices and vectors lifted to higher-dimensional tensors point-wise

Equally what is matrix multiplication but a bunch of 1-dimensional dot products applied pointwise? why do we need matrices?

I do get what you're saying, and that part of it is that ML / CS folk just use 'tensor' as a fancy word for a multi-dimensional array, whereas physics folk use the word for a related coordinate-basis-independent geometric concept. But for numerical computing broadcasting simple operations over slices of some big array is really useful thing to be able to do fast and to express concisely.

Numerics libraries which don't bother to generalise arrays beyond rank 1 and 2 always feel rather inelegant and limiting to me. Rank 3+ arrays are often really useful (images, video, sensory data, count data grouped by more than 2 factors, ...), and lots of operations generalise to them in a nice way. Good array programming environments (numpy, torch, APL take advantage of this to provide an elegant general framework for broadcasting of operations without ugly special cases.

Re: TensorFlow: open-source library for machine intelligence

#153

Post by sytelus »

Fede_V wrote: post #87
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…

One small note on the paper itself. I love that the paper's author are in alphabetical orders, without any stupid jostling over first/last authorship. I think that's fantastic and wish academia went that way too (yeah right).

Why is alphabetical order great? It just only means that people with last names starting with z will get penalized every single time because of choosing wrong parents! I would think randomized order would be chosen - especially if you were mathematician.

Re: TensorFlow: open-source library for machine intelligence

#154

Post by auston »

Many many thanks in advance to anyone who answers:

I've futzed around with ML docs (dataquest, random articles, first 3 weeks of andrew ng course on coursera) & what I don't get about this (http://tensorflow.org/tutorials/mnist/beginners/index.md) is how to actually make a prediction / classification on something that is not "test" data. Can anyone point me in the right direction of how to "use" a model once I have it validated, like we do at the end of that tutorial?

Re: TensorFlow: open-source library for machine intelligence

#155

Post by zeroxfe »

Nitramp wrote: post #84

Maybe of interest: this is (amongst others) by Jeff Dean, famous for Bigtable, Map Reduce, Spanner, Google Web Search, Protocol Buffers, LevelDB, and many, many other things. He's a Google Senior Fellow, but also doubles as the patron saint of Google Engineering.

He is also a ninja, an astronaut, a master chef, and a damn good fellow!

Re: TensorFlow: open-source library for machine intelligence

#157

Post by HockeyPlayer »

Anyone experienced with machine learning want to try this out on some high frequency trading data? I'm in the processing of preparing a data set for more traditional analysis and would be willing to share.

We are in Colorado, but I'm happy to work with someone remotely.

Re: TensorFlow: open-source library for machine intelligence

#158

Post by davmre »

sandGorgon wrote: post #122

what would be really awesome is if Andrew Ng or Norvig build a course around Tensorflow. It is really not useful to a beginner to be learning everything in matlab.

There are already a few university ML courses out there using Theano (for which Tensorflow is essentially a drop-in replacement), and I think this will be a much bigger trend over the next few years. IMHO for a first course it's useful to do some work at the Matlab/numpy level just so you get experience with deriving/implementing gradients yourself, but for larger (deep) models automatic differentiation is an amazing productivity boost that should make it possible to cover a lot of interesting topics that you'd otherwise not have space for.

Re: TensorFlow: open-source library for machine intelligence

#159

Post by davmre »

tdaltonc wrote: post #98
aconz2 wrote: post #6

> This open source release supports single machines and mobile devices. Can someone clarify if "single machines" means the Apache license only applies to single machines and not distributed systems? Sidenote: I wish every open source project had a release video.

Is it common for code to open sourced, but only for use on single machines?

The distributed part of the system probably depends on other components of Google's proprietary infrastructure, e.g., for cluster job scheduling. So it's a bit of work to tear that out and replace with something that's externally usable. I can't tell whether they've committed to doing that, but I hope they do.

Re: TensorFlow: open-source library for machine intelligence

#160

Post by Zephyr314 »

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…

Depending on how long it takes to "evaluate the goodness of a solution" techniques like multi-start gradient decent can rapidly become intractable though, especially in higher dimensions. There are a handful of open source libraries out there that try to tackle this time consuming and expensive black box optimization problem from a more Bayesian approach [1] [2]. There's also a YC company to do this as a service (full disclosure, I'm a co-founder) [3]. Combining these methods with TensorFlow could be very powerful and is one step closer to more automatic ML flows though.

[1]: https://github.com/Yelp/MOE (full disclosure, I co-wrote this)

[2]: https://github.com/hyperopt/hyperopt

[3]: https://sigopt.com/cases/machine_learning

Post reply on HN