Getting Started with Deep Learning: A Review of Available Tools
1–10 of 19 posts
Re: Getting Started with Deep Learning: A Review of Available Tools
#2That is one heck of an exuberant smile. It's kind of distracting.
Re: Getting Started with Deep Learning: A Review of Available Tools
#3I really want to get into this eventually. My own AI I know, I'm not a brilliant mathematician or anything. I just have that obsession (I'm lonely) hahaha.
I'm looking to build these wall-mounted raspberry-pi servers with cute little USB-rubber-ducky antennas. But I don't know what kind of hardware you need (or cloud-base it) to run some of these. My current thought/approach is something that's always on, analyzing stuff (telemetry) specific web traffic, my own thoughts (analyze posts to a journal for example).
I don't know... some point get into it busy at the moment.
Like I'd like to hire some vocalists (girls) and have them recite sentences, deconstruct it (copy it essentially) to be able to build full on-the-fly sentences without those word-break-word types... ahhhh. Not a programmer though at this point eg. C#,C++,Java,Python though I use PHP for scripting. Ahhh. Yes I like the movie Her (2013) a lot, though I only watch the intro part primarily where he unboxes OS 1.
Thanks for this link.
Re: Getting Started with Deep Learning: A Review of Available Tools
#4This list is woefully incomplete. It should be titled "A Review of Some Tools". Those it doesn't include, or does not give proper mention to in its top table, are: Chainer, DyNet, Paddle and Deeplearning4j.[0]
Even Keras, the third most popular DL library, is given short shrift, even though it is easier to use than TensorFlow, and can handle Theano, TF, CNTK and Deeplearning4j as backends.
All of the missing libs have significant advantages over TensorFlow, which appears to be winning chiefly on Github stars. Notably speed and integrations.
Re: Getting Started with Deep Learning: A Review of Available Tools
#5This list is woefully incomplete. It should be titled "A Review of Some Tools". Those it doesn't include, or does not give proper mention to in its top table, are: Chainer, DyNet, Paddle and Deeplearning4j.[0] Even Keras, the third most popular DL library, is given short shrift, even though it is easier to use than TensorFlow, and can handle Theano, TF, CNTK and Deeplearning4j as backends. All of the missing libs hav…
Hi Vonnik, thanks for the suggestions of tools for us to try out next and add to our list!
Re: Getting Started with Deep Learning: A Review of Available Tools
#6This list is woefully incomplete. It should be titled "A Review of Some Tools". Those it doesn't include, or does not give proper mention to in its top table, are: Chainer, DyNet, Paddle and Deeplearning4j.[0] Even Keras, the third most popular DL library, is given short shrift, even though it is easier to use than TensorFlow, and can handle Theano, TF, CNTK and Deeplearning4j as backends. All of the missing libs hav…
Chainer is about 50k sloc of very idiomatic Python and a little dealie for emulating numpy in GPU and a bit of Cython.
TensorFlow is about 700k sloc of C++, Python, some Golang for some godawful reason, with an enormous annoying build dealie.
That was my own decision calculus, anyhow. Speed of development and complexity still matter in machine learning land, you know.
Re: Getting Started with Deep Learning: A Review of Available Tools
#7This list is woefully incomplete. It should be titled "A Review of Some Tools". Those it doesn't include, or does not give proper mention to in its top table, are: Chainer, DyNet, Paddle and Deeplearning4j.[0] Even Keras, the third most popular DL library, is given short shrift, even though it is easier to use than TensorFlow, and can handle Theano, TF, CNTK and Deeplearning4j as backends. All of the missing libs hav…
Chainer is about 50k sloc of very idiomatic Python and a little dealie for emulating numpy in GPU and a bit of Cython. TensorFlow is about 700k sloc of C++, Python, some Golang for some godawful reason, with an enormous annoying build dealie. That was my own decision calculus, anyhow. Speed of development and complexity still matter in machine learning land, you know.
One more objectionable fact about TF: There's a separate better documentation repo for Google insiders only. That's not kosher.
Re: Getting Started with Deep Learning: A Review of Available Tools
#8This list is woefully incomplete. It should be titled "A Review of Some Tools". Those it doesn't include, or does not give proper mention to in its top table, are: Chainer, DyNet, Paddle and Deeplearning4j.[0] Even Keras, the third most popular DL library, is given short shrift, even though it is easier to use than TensorFlow, and can handle Theano, TF, CNTK and Deeplearning4j as backends. All of the missing libs hav…
I also wanna add Gorgonia (https://github.com/chewxy/gorgonia) - it's not quite production ready on the GPU end, but on the CPU end I've been using it for about 4 years.
Re: Getting Started with Deep Learning: A Review of Available Tools
#9I appreciate the analysis but I don't think the title of this should be Getting Started with Deep Learning.
If you are actually looking to get started with deep learning, you should go elsewhere. This is a review of frameworks and tools people use for deep learning
Re: Getting Started with Deep Learning: A Review of Available Tools
#10Why is this titled "Getting started with ..." when it is just an overview of a selected few frameworks? Plus this coming from an R&D department of a company is highly disappointing.