TensorFlow 1.0 Released • Hacker News Board

Re: TensorFlow 1.0 Released

#71

Post by nojvek » Thu, Feb 16, 2017, 5:03 PM UTC

xtf wrote: post #69

nojvek wrote: post #68

Earlier quoted context omitted.

Running neural nets on a standard mobile device will be game changing. I can't wait for mobile devices having custom chips to do AI related tasks. I'm predicting in a decade we'll have offline speech and image recognition running on the phone.

They don't want you to go there. Remind who started the latest big AI Projects (Google, Amazon, Microsoft, Facebook) and I don't think the will stop grabbing data. I think they'll develop a hivemind, where mobile adds to the pool. In short Skynet ;)

Hopefully the ASICs are fast and open enough so we can see some open AIs who respect our privacy and security concerns

Re: TensorFlow 1.0 Released

#72

Post by p1esk » Thu, Feb 16, 2017, 8:17 PM UTC

andy_ppp wrote: post #56

p1esk wrote: post #55

Earlier quoted context omitted.

TensorFlow is not a clone of Theano. It's based on the earlier Google's platform DistBelief, mostly known outside of Google as the engine behind 2012 Youtube cat videos paper. Like DistBelief, TensorFlow was designed from the ground up to be scalable across multiple nodes. Theano, on the other hand, seems to be focused on the optimizations for the single machine, single GPU code. It only recently got the ability to r…

To be truthfully honest it doesn't matter either way or even if there is something "better" out there (if Theranos was...). TensorFlow has already become the winner from my reading around it so I'm going to continue learning it rather than another framework until I've become fairly proficient. By which time why change?

TensorFlow does not make AI or DL "more accessible". It's not easier to use than Theano. Both have good documentation, and both have lots of code examples/model implementations.

If you're looking for something that would make it easier for you to learn DL, you should try Keras - it's a higher level library, which can use both Theano and TF as a backend.

Re: TensorFlow 1.0 Released

#73

Post by drakonka » Fri, Feb 17, 2017, 2:40 PM UTC

emmelaich wrote: post #59

Omnipresent wrote: post #36

Earlier quoted context omitted.

Do you have a link to the said book?

Must be https://www.safaribooksonline.com/library/view/learning-tens... To be released in June.

Yes, that's the one.

Re: TensorFlow 1.0 Released

#74

Post by alvivar » Sat, Feb 18, 2017, 8:31 PM UTC

I wish so much for experimental APIs compatible with .Net stuff. Mostly because I want to use it with F#.

I really like Python, but F# <3

Re: TensorFlow 1.0 Released

#75

Post by chrisra » Tue, Feb 21, 2017, 10:23 PM UTC

120bits wrote: post #70

For a complete beginner. What kind of applications I can work on using TensorFlow?

One of the "Hello, World" applications would be learning to classify MNIST digits. They have a tutorial on their site.

Re: TensorFlow 1.0 Released

#76

Post by ghego » Thu, Feb 23, 2017, 2:55 AM UTC

cstuder wrote: post #10

How do I get started with machine learning? I have a couple of applications in mind, mostly time series predictions. But the machine learning field seems to be vast and I don't know where to start.

if you are based in the SF Bay Area you can come to Data Weekends (www.dataweekends.com). They are 2-day workshops to get started with Machine Learning and Deep Learning (full disclosure: I run them)