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

Jeff Dean explains TensorFlow [video]

youtube.com

Post reply on HN
Print view View original

61–70 of 71 posts

Re: Jeff Dean explains TensorFlow [video]

#61

Post by olooney »

pritambaral wrote: post #59
AMEDICALRe wrote: post #53

Earlier quoted context omitted.

Torch has extremely difficult learning curve due to Lua. With Tensor Flow underlying engine in C++ it is likely as efficient as Torch. Special extension such as Nvidia Cudnn could also be used with tensorflow.

What do you mean by "diffcult learning curve due to Lua"? Lua isn't difficult. Lua is easier than JavaScript! Or perhaps you mean to say that Torch itself is difficult to learn because of design choices that were made in order to use Lua?

Learning an entirely new language for a project, no matter how simple that language is, is certainly a barrier to entry.

Re: Jeff Dean explains TensorFlow [video]

#62

Post by ambiate »

IshKebab wrote: post #34
codyguy wrote: post #16

Yay!! An open sourced voice engine in the future? That would really shake things up.

No. a) Stuff similar to this has been available for ages and there are no (good) open source voice recognition packages. b) It requires absolute mountains of training data which we don't have. c) It requires designing a suitable network, which I'm not sure if we have, but I would doubt it. d) It requires training a network on the mountains of training data using an immense computing cluster, which we requires money t…

Sometimes creativity is the only thing holding people back from exploiting the natural insects of the web.

Case in point, ever wonder why those captchas include street addresses or 'pick the shape with a hole in it?' Spoiler: you're building training data and validating training data.

How else can we silently retrieve training data?

Re: Jeff Dean explains TensorFlow [video]

#63

Post by chm »

shostack wrote: post #23
chm wrote: post #12

Earlier quoted context omitted.

I'm dying for this stuff to be dumbed down enough[...] It kind of already is. Have you read the docs/examples? I don't think your mentality is fruitful. Having argued with people who shared your point of view, it seems there will always be something too difficult that prevents them from being good at X. There's no substitute for sweat. Have fun with the code they gave you and see where you end up!

I think we have different definitions of what "dumbed down" means. I never said I could/would never put in the work to learn it. I'm saying that the place it is in right now is still too advanced for someone with my background to pick up and play around with without sitting down to seriously study the underlying concepts that are objectively fairly dense subject matter that can require advanced math and CS background…

Hi Shostack,

I wasn't trying to bring you down. Maybe what you're looking for is a visual programming environment, where you can drag and drop functions, data, etc?

Re: Jeff Dean explains TensorFlow [video]

#64

Post by smhx »

lacksconfidence wrote: post #20
miket wrote: post #17

Earlier quoted context omitted.

Here's a page with various benchmarks: https://github.com/soumith/convnet-benchmarks An issue has been created to add TensorFlow to this shortly.

This looks to be a single machine test, where this video and the poster above specifically talked about running against compute clusters. I don't think a single machine benchmark is going to be nearly as interesting.

They didn't release the multi-machine version of TensorFlow. They said they're still working on it and will release it when it's ready.

Re: Jeff Dean explains TensorFlow [video]

#65

Post by T-A »

shostack wrote: post #8

Is there anything an "early" programmer like myself can do to play around with this stuff without a background in the related math? I'm dying for this stuff to be dumbed down enough where Joe WebUser can feed in arbitrary data in a csv or point an app at a data source and get some sort of meaningful results. It truly seems like an area where once the barrier to entry is greatly reduced, the creativity of laymen will…

Maybe try some of cloud-based machine learning offerings like

https://studio.azureml.net/

http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl...

https://cloud.google.com/prediction/docs

Re: Jeff Dean explains TensorFlow [video]

#66

Post by argonaut »

AMEDICALRe wrote: post #53
mtw wrote: post #48

Earlier quoted context omitted.

Torch is used in production by Facebook , deepmind and possibly baidu, amongst others. Facebook especially have released code to make torch run much faster on AWS with GPU cards. Also no startup time. The design is done with a high level language (lua) while computation done mostly in C. I'd be very surprised if tensorflow is actually faster than torch on a single machine

Torch has extremely difficult learning curve due to Lua. With Tensor Flow underlying engine in C++ it is likely as efficient as Torch. Special extension such as Nvidia Cudnn could also be used with tensorflow.

If somebody finds learning Lua to be difficult, then learning C++, learning basic statistics, or learning machine learning will be impossible for them.

Re: Jeff Dean explains TensorFlow [video]

#67

Post by argonaut »

EwanToo wrote: post #60
argonaut wrote: post #57

Earlier quoted context omitted.

Way off. He's a Senior Google Fellow and his bio used to be on the executive leadership page of Google (I can't find that page any more). He is being paid on the order of 10MM per year, base, easily.

Perhaps, I doubt his salary is that high, but he'll have significant amounts of of stock grants, options, etc. Executive compensation is a very odd area, as I said, it pretty much depends how much money he wants.

Yeah I should have been more clear. But I'm pretty sure his equity alone is more than $30M / year.

Re: Jeff Dean explains TensorFlow [video]

#68

Post by shostack »

chm wrote: post #63
shostack wrote: post #23

Earlier quoted context omitted.

I think we have different definitions of what "dumbed down" means. I never said I could/would never put in the work to learn it. I'm saying that the place it is in right now is still too advanced for someone with my background to pick up and play around with without sitting down to seriously study the underlying concepts that are objectively fairly dense subject matter that can require advanced math and CS background…

Hi Shostack, I wasn't trying to bring you down. Maybe what you're looking for is a visual programming environment, where you can drag and drop functions, data, etc?

Not sure I even need a visual programming environment as I'm comfortable using a command line and hacking stuff together in Sublime.

However I am highly visual and visualizing the impact on the results would be really helpful. I deal with a lot of analytics and data as part of my day-to-day managing digital media. I often find that I can easily spot trends just by glancing at data visualizations, and infer insights from them.

Further, being able to visualize the nature of the functions/data/etc. would also be very helpful. I tend to need to visualize something to fully grok it.

If you have any suggestions for a more visual take on machine learning that is beginner friendly, I'd love a link.

Re: Jeff Dean explains TensorFlow [video]

#69

Post by catwell »

olooney wrote: post #61
pritambaral wrote: post #59

Earlier quoted context omitted.

What do you mean by "diffcult learning curve due to Lua"? Lua isn't difficult. Lua is easier than JavaScript! Or perhaps you mean to say that Torch itself is difficult to learn because of design choices that were made in order to use Lua?

Learning an entirely new language for a project, no matter how simple that language is, is certainly a barrier to entry.

If you have already used another dynamic, imperative language, you can probably learn enough Lua to use Torch effectively in 30 minutes.

Seriously, there are three features in the Lua language which are not trivial: metatables, coroutines and _ENV. None of those are needed to use Torch.

It will take more time to learn Torch-specific APIs, but the same problem exists with the other ML frameworks.

Re: Jeff Dean explains TensorFlow [video]

#70

Post by shammo »

cafebeen wrote: post #55
shostack wrote: post #8

Is there anything an "early" programmer like myself can do to play around with this stuff without a background in the related math? I'm dying for this stuff to be dumbed down enough where Joe WebUser can feed in arbitrary data in a csv or point an app at a data source and get some sort of meaningful results. It truly seems like an area where once the barrier to entry is greatly reduced, the creativity of laymen will…

It's probably best to understand what you're doing if you use something like this. I'd recommend at least going through an intro ML book/course to learn the basics first.

any suggestions on good intro ML books?
Post reply on HN