Leaf: machine intelligence framework in Rust

It&#x27;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 &quot;machine intelligence&quot; [1], which could mean so many things.<p>Otherwise, it&#x27;s great to see such initiatives in Rust. I&#x27;m unsure if there&#x27;s an equivalent that implements more traditional ML algorithms (logistic regression, decision tree, random forest, SVM, etc.)<p>[1] <a href="https:&#x2F;&#x2F;github.com&#x2F;autumnai&#x2F;leaf&#x2F;commit&#x2F;58bfa92abd5721eae116b44e86103cbd850aee23#diff-04c6e90faac2675aa89e2176d2eec7d8" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;autumnai&#x2F;leaf&#x2F;commit&#x2F;58bfa92abd5721eae116...</a>

Great work -- very exciting to see a Rust ML framework!<p>Dist-Belief (TensorFlow&#x27;s predecessor) was oriented around layers (as Leaf is) but TensorFlow (like Theano) is graph&#x2F;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&#x2F;forward passes.<p>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).

I 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 &quot;smarter&quot; language moreso than the not-offloaded-to-C performance (do people care what they code gets compiled to?)<p>I was pretty excited about the tensorflow announcement but I&#x27;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)<p>Your product, Autumnai, sounds exciting as well

Since there seems to be an uptick in submissions related to machine intelligence projects lately (or rather since Google released <a href="http:&#x2F;&#x2F;tensorflow.org" rel="nofollow">http:&#x2F;&#x2F;tensorflow.org</a>) (e.g. <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=10537697" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=10537697</a>) does anyone dare to make a comparison?<p>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.

&gt; Leaf is a open source framework for machine intelligence, sharing concepts from TensorFlow and Caffe.<p>That was fast. (Like, I know that&#x27;s a documentation change, but stil.)

Exciting to see this! I haven&#x27;t taken a look at TensorFlow code yet but it looks very similar (method names and all) to Caffe. I&#x27;ve wanted a CNN library for Rust for a while.<p>It sounds like performance is important to you. Are there any plans to add GPU paths soon? If it&#x27;s CUDA, are you going to use cuDNN?

I like your idea very much, especially implement in Rust. As we need more powerful computation, the native low-level language is a very good choose, we can control the memory, and call the native library to run on CPU&#x2F;GPU.<p>Even the development of Rust may not very high enough compared with Java&#x2F;Go(I do not sure), but we can keep the core as simple and steady, and use high-level language such as Python&#x2F;R to implement the API.<p>Hope to hear more wonderful news about this Project.