intro update

docs/make.jl

@@ -8,7 +8,7 @@ makedocs(modules=[Flux],
          assets = ["../flux.css"],
          pages = ["Home" => "index.md",
                   "Getting Started" => [
-                    "Basics" => "mnist.md"]])
+                    "Basics" => "basics.md"]])
 
 deploydocs(
    repo = "github.com/MikeInnes/Flux.jl.git",

docs/src/basics.md

@@ -0,0 +1,3 @@
+# Basic Usage
+
+## *Charging Ion Capacitors*

docs/src/index.md

@@ -1,9 +1,9 @@
 # Flux
 
-## Charging Ion Capacitors
+Flux is a high-level interface for machine learning, implemented in Julia.
 
-Flux is a high-level API for machine learning, implemented in Julia.
+Flux aims to be intuitive and powerful notation close to the mathematics, while providing advanced features like auto-unrolling and closures. Simple models are trivial, and the most complex architectures are tractable, taking orders of magnitude less code than in other frameworks. Meanwhile, the Flux compiler provides excellent error messages and tools for debugging when things go wrong.
 
-Flux aims to provide a concise and expressive syntax for architectures that are hard to express within other frameworks. The notation should be familiar and extremely close to what you'd find in a paper or description of the model.
+So what's the catch? Flux is at an early "working prototype" stage; many things work but the API is still in a state of- well, it might change.
 
-The current focus is on ANNs with TensorFlow or MXNet as a backend.
+If you're interested to find out what *does* work, read on...

docs/src/mnist.md

@@ -1 +0,0 @@
-# MNIST