Slashdot Mirror
With TensorFlow, Google Open Sources Its Machine Learning Resources (blogspot.com)
smaxp writes: Google has announced the open source release of TensorFlow, its machine learning software library. "TensorFlow has extensive built-in support for deep learning, but is far more general than that -- any computation that you can express as a computational flow graph, you can compute with TensorFlow (see some examples). Any gradient-based machine learning algorithm will benefit from TensorFlow’s auto-differentiation and suite of first-rate optimizers. And it’s easy to express your new ideas in TensorFlow via the flexible Python interface." This comes alongside some dramatic speed increases (PDF). The code is available at GitHub under an Apache 2.0 license. "Deep learning, machine learning, and artificial intelligence are all some of Google's core competencies, where the company leads Apple and Microsoft. If successful, Google's strategy is to maintain this lead by putting its technology out in the open to improve it based on large-scale adoption and code contributions from the community at large.
I'm using it in production to learn when Google will discontinue the service and force me to start shopping for an alternative.
I'm training it using the history of projects such as Knol, Talk, iGoogle, Reader, notebook , Buzz, Labs, Wave, answers, etc.
If the training works, it may be able to tell me the most likely replacement, before they get bought out and go public.
What is the rationale behind borrowing the name from differential geometry? Can we find any examples in the library where the knowledge of differential geometry is applied to machine learning?
Dog eyes! Dog eyes everywhere!
Proof the google is evil and inimical to teh intarwebz.
the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff
As in the summary, they claim that Tensorflow is a machine learning software library. That sounds cool and conjures thoughts of artificial or machine intelligence, self learning computers...
But, the Tensor flow page starts with
TensorFlow is an open source software library for numerical computation using data flow graphs
Which sounds very mundane and not at all like artificial intelligence or self learning.
Can anyone explain what it really is or is capable of and what it is used for?
Just because it's not useful to you, doesn't mean it's not useful to anyone.
Now go deliver me a pizza.
"Did you mean The liberal me appeases? Here is a list of possible liberal appeasers in your neighborhood."
STFU Siri! I'm sick of your shit.
It's an interesting library but the poster is getting way ahead of himself, to the point of looking more like marketing or fanboyism than anything else.
For instance, he claims that TensorFlow comes with "dramatic speed increase" and offers as proof a link to a paper where there is no such proof and, indeed, the 'performance' section contains only the following sentence : "A future version of this white paper will have a comprehensive performance evaluation section of both the single machine and distributed implementations."
Yet another very interesting move by Google. Am I overenthusiastic? Will this become a reference framework that it's sufficient to learn to stand at the bleeding edge of the latest deep learning techs?
Right now this field is evolving so fast, there's no reason to commit to a particular library since there's no way to know what data structure / model / training regimen will prove to be superior. Any good framework achieving dominance (lets you quickly try out whatever another team came up) with will do the trick. Google's one of the top dogs in the field and has already made public many deep learning research products. So there's a high chance they'll succeed with this move, right?
I'm guessing their expected benefit is 1) their own teams just get to stay in known waters 2) good image / attracting talents [ 3) they're the ones that get to father the AI that takes over ]
Or rather a graph. The models and computations are represented by an acyclic graph, with standard back propagation being a reverse step through the forward direction of the computation. This is the fundamental and most surprising thing about current ai. It's not computationally surprising, there are no convoluted maths ( but some convolution) and it is cheaper than ever before.
Maybe I misread the tensor page, but it looks like the installation is linux/mac only? If so, are they open-sourcing it trying tro drive people awya from Windows?
I mean, it's open source, so if that were the case there would be a Windows version PDQ. But it wouldn't be offical, needing to be updated by a third party.
Your ad here. Ask me how!
Looks pretty similar to the many other neural net libraries out there -- especially Theano's data flow graphs. But distributed more like Hadoop's DeepLearning4j. And like all the over-hyped "deep learning" tools, it's for running same backprop algorithms that we had in the 1980s... So what the new exciting part then ? Just that's it's production software engineered code rather than a research implementation?
I'm still not clear on how this is machine learning.
What you describe sounds, to me, more like categorization or a database lookup against definitions or templates. For example fuzzy hash of picture == cat. Fuzzy hash of next picture also very similar to cat == cat.
I would have expected machine learning to be more akin to self programming, where the machine develops its own algorithm or functions to complete a new operation that it was not initially programmed to do. For example, it's programmed to recognize a cat and it "learns" to hiss or purr when it sees one.