Also it seems to use the standard method of stacking layers, rather than allowing you to describe an arbitrary computational graph which seems (to me) to be the far superior method (see CNTK's Network Description Language).
Leaf takes an imperative approach and explores an easier API (only Layers (Functions)[1] and Solvers (Optimizer Algorithms)), reusability through modularity and abstractions that keep the implementation and concepts to a minimum or rather abstractions that feel as familiar to a hacker as possible.
For future versions e.g., we want to explore what is practically possible with auto-differentiation via dual numbers and differentiable programming.
[1]: http://autumnai.com/leaf/book/deep-learning-glossary.html#La...
Of course, most people don't have the resources of Google with a layer of data scientists and another layer of software engineers [and maybe a layer of data engineers in the mix too]. So the idea of a tool tailored to a small team's needs rather than those of Google seems like an interesting niche.
> Leaf is a Machine Intelligence Framework engineered by hackers, not scientists. It has a very simple API...
That is quite a diferentiator.