Leaf: machine intelligence framework in Rust
1–10 of 20 posts
Re: Leaf: machine intelligence framework in Rust
#2It's unfortunate that just because Tensor Flow was released, you felt the need to replace references to deep learning (which is a somewhat well-defined application) by "machine intelligence" [1], which could mean so many things.
Otherwise, it's great to see such initiatives in Rust. I'm unsure if there's an equivalent that implements more traditional ML algorithms (logistic regression, decision tree, random forest, SVM, etc.)
[1] https://github.com/autumnai/leaf/commit/58bfa92abd5721eae116...
Re: Leaf: machine intelligence framework in Rust
#3Since there seems to be an uptick in submissions related to machine intelligence projects lately (or rather since Google released http://tensorflow.org) (e.g. https://news.ycombinator.com/item?id=10537697) does anyone dare to make a comparison?
I am currently just getting started in this area due to my interest in AI and I am not quite sure which route to choose.
Re: Leaf: machine intelligence framework in Rust
#4It's unfortunate that just because Tensor Flow was released, you felt the need to replace references to deep learning (which is a somewhat well-defined application) by "machine intelligence" [1], which could mean so many things. Otherwise, it's great to see such initiatives in Rust. I'm unsure if there's an equivalent that implements more traditional ML algorithms (logistic regression, decision tree, random forest, S…
We wanted to make clear that we are not "just" doing deep learning with Leaf. A lot of other ML algorithms that don't fall under the deep learning label can benefit of the tools provided (e.g. solvers) and can be implemented as layers. While not too popular, there are papers showing this being done with e.g. a SVM[0].
[0] http://deeplearning.net/wp-content/uploads/2013/03/dlsvm.pdf
Re: Leaf: machine intelligence framework in Rust
#5Since there seems to be an uptick in submissions related to machine intelligence projects lately (or rather since Google released http://tensorflow.org ) (e.g. https://news.ycombinator.com/item?id=10537697 ) does anyone dare to make a comparison? I am currently just getting started in this area due to my interest in AI and I am not quite sure which route to choose.
MJ here - founder of Autumn and creator of Leaf.
I can give a quick comparison on Leaf vs. TensorFlow - although this might seem somewhat biased.
We like what the Google engineers did on TensorFlow and share a lot of similar ideas on how future Machine Learning should be structured and implemented. Especially that in the end it is just a performant pipeline for numeric information processing.
We feel that the biggest difference (besides the different stages of the project) is the language and the ecosystem that it embraces. We are strong believers in Rust and think that it might have good chances to succeed in the long run - which we outline in more detail in the Q&A[1].
Due to your question I would recommend picking up on the basic concepts of machine intelligence and then going with whatever ecosystem fits the task/stack. Might become similar to choices of web frameworks in the next couple of years. I think Neon[2] - as a Python framework - seems to be easy and performant as well.
[1]: https://github.com/autumnai/leaf#why-rust [2]: https://github.com/NervanaSystems/neon
Re: Leaf: machine intelligence framework in Rust
#6Since there seems to be an uptick in submissions related to machine intelligence projects lately (or rather since Google released http://tensorflow.org ) (e.g. https://news.ycombinator.com/item?id=10537697 ) does anyone dare to make a comparison? I am currently just getting started in this area due to my interest in AI and I am not quite sure which route to choose.
If you're just getting started in this area (machine learning), I'd advise you to look at simpler and more interpretable models first (things like logistic regression, decision tree, perceptron) using simple tools (scikit-learn for instance).
Something like Tensor Flow has a lot of mechanics you have to understand before getting started, and it's "lower-level" than other ML libraries. And I definitely wouldn't advise you to use "deep learning" as your first ML model. It's hard to understand, and the result of training it is hard to interpret.
Re: Leaf: machine intelligence framework in Rust
#7I am very excited to finally see this type of library in a modern (strongly typed) language, let alone my current passion language. In my opinion your pitch (ok, Readme), should put emphasis on the productivity and usability gain of types and a generally "smarter" language moreso than the not-offloaded-to-C performance (do people care what they code gets compiled to?)
I was pretty excited about the tensorflow announcement but I'm actually saddened that it might cast a shadow over this library, which in my opinion brings more to the arena (e.g. improvements on the current scripting approach of theano, torch et. al)
Your product, Autumnai, sounds exciting as well
Re: Leaf: machine intelligence framework in Rust
#8> Leaf is a open source framework for machine intelligence, sharing concepts from TensorFlow and Caffe.
That was fast. (Like, I know that's a documentation change, but stil.)
Re: Leaf: machine intelligence framework in Rust
#9Great work -- very exciting to see a Rust ML framework!
Dist-Belief (TensorFlow's predecessor) was oriented around layers (as Leaf is) but TensorFlow (like Theano) is graph/flow-based rather than layer-based. I think in particular the layer-based approach makes it awkward to represent more complicated models since not every model can be decomposed into backward/forward passes.
Do you worry that by adopting a layer-based paradigm you are boxing yourself in? A graph-based approach does seem more flexible (and distributable across machines).
Re: Leaf: machine intelligence framework in Rust
#10Exciting to see this! I haven't taken a look at TensorFlow code yet but it looks very similar (method names and all) to Caffe. I've wanted a CNN library for Rust for a while.
It sounds like performance is important to you. Are there any plans to add GPU paths soon? If it's CUDA, are you going to use cuDNN?