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

71–80 of 211 posts

Re: TensorFlow: open-source library for machine intelligence

#71

Post by elcritch »

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…

Agreed, this is huge. I've been thinking along these lines for a while, but more focused on traditional programming systems. The approach of programming via data-flows and visually representing those is going to be enormous in the coming decade, IMHO. Especially in asynchronous and heterogenous programming environments.

Actually, it feels like I've been "scooped" somewhat. However, at the same time it's awesome to find that many of the core assumptions I've been working in formulating for traditional programming systems are actually already being used by other top engineers/researchers at Google. Thanks for posting about the whos-who of systems research. I'll have to check up on their research more!

I think there is a lot of room left to apply this approach to a lot of existing systems outside of machine learning. We're working on releasing a prototype in the coming months at our new startup (vexpr.com) based on applying these same data-flow principles to normal programming projects. Actually this might give a huge boost in presenting the underlying approach to systems engineering to audiences.

Re: TensorFlow: open-source library for machine intelligence

#72

Post by irq-1 »

This looks similar to Orange. Orange has a visual designer, easy data access (SQL, arbitrary files) and lots of widgets, but it's a desktop tool not a library and doesn't standardize the data structures.

http://orange.biolab.si/

http://docs.orange.biolab.si/widgets/rst/index.html

Re: TensorFlow: open-source library for machine intelligence

#73

Post by varelse »

rhaps0dy wrote: post #61
varelse wrote: post #56

Earlier quoted context omitted.

Methinks embrace the magical library written by engineers and researchers at Google instead of by a random goulash of machine learning grad students with no investment in the outcome other than graduating.

> with no investment in the outcome other than graduating Come on. Grad students are motivated by advancing the field. ... are they not? Maybe you can also be saying that the ones who write libraries are motivated only by graduating.

Sure, we all start out that way. But by the 3rd or 4th year, you frequently just want to write that thesis and get on to the next thing because you've already advanced the field as much as you're going to as a grad student.

I have a large package of code on sourceforge that consists of my grad school and postdoctoral efforts. If I compare its style to what 2 decades in the industry since has taught me, it's laughable. That said, it is C code, so I occasionally plunder it for algorithms I figured out way back when.

Re: TensorFlow: open-source library for machine intelligence

#74

Post by dswalter »

doczoidberg wrote: post #62

I am a newbie to machine learning. How does it compete to Azure ML besides it is open source?

It's not really directly comparable. This is a computational framework which you can use to implement a variety of ML algorithms (or in general numerical computation), so the interface to this is lower-level than Azure ML.

If Azure ML is a bunch of premade sandcastle molds, TensorFlow is a more accurate, faster way to pour sand. You make the mold.

Re: TensorFlow: open-source library for machine intelligence

#77

Post by varelse »

pacala wrote: post #55
varelse wrote: post #37

Earlier quoted context omitted.

And just 4 years after their insistence that GPUs would never have a role at Google... How 'bout that?

Google is a big place, with diverse opinions. Even better, it encourages updating one's opinion in face of new evidence. GPUs have proven themselves cost-effective in tackling a number of vision problems [and others], Google has those problems, so the opinion was updated and the problems were solved in a cost-effective manner.

That... Was not... My experience there...

But kudos to the deep learning guys for overcoming that potential energy barrier NVIDIA couldn't surmount on their own...

Re: TensorFlow: open-source library for machine intelligence

#78

Post by xyzzyz »

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…

I'd say tensor is exactly as confusing as vector -- vectors are just elements of some vector spaces, and you get a list of numbers by choosing a basis of that vector space. Similarly, tensors are just elements of a tensor product of some vector spaces (or modules), and you get a multidimensional array by choosing bases in the factors.

Re: TensorFlow: open-source library for machine intelligence

#80

Post by ska »

varelse wrote: post #69
pilooch wrote: post #64

Earlier quoted context omitted.

Google is certainly Nvidia's top customer.

Sure, now. 4 years ago, not so much. One might even conclude that one person inside Google had written a brawny and influential paper that was right in a lot of ways, but wimpily dead-wrong to apply to GPUs.

Might one conclude that getting hung up on one opinion from a large group of people projected forward in time is... not very useful?
Post reply on HN