diff --git a/latest/apis/backends.html b/latest/apis/backends.html index 336dba35..d6c838b4 100644 --- a/latest/apis/backends.html +++ b/latest/apis/backends.html @@ -150,7 +150,7 @@ Backends - + diff --git a/latest/apis/batching.html b/latest/apis/batching.html index 7501e711..70087a62 100644 --- a/latest/apis/batching.html +++ b/latest/apis/batching.html @@ -155,7 +155,7 @@ Batching - + diff --git a/latest/apis/storage.html b/latest/apis/storage.html index 4e11f607..6d1097c0 100644 --- a/latest/apis/storage.html +++ b/latest/apis/storage.html @@ -139,7 +139,7 @@ Storing Models - + diff --git a/latest/contributing.html b/latest/contributing.html index c62c3a08..796acf85 100644 --- a/latest/contributing.html +++ b/latest/contributing.html @@ -136,7 +136,7 @@ Contributing & Help - + diff --git a/latest/examples/char-rnn.html b/latest/examples/char-rnn.html index 0e5fd42e..f9cfb057 100644 --- a/latest/examples/char-rnn.html +++ b/latest/examples/char-rnn.html @@ -139,7 +139,7 @@ Char RNN - + diff --git a/latest/examples/logreg.html b/latest/examples/logreg.html index 11595752..616f3464 100644 --- a/latest/examples/logreg.html +++ b/latest/examples/logreg.html @@ -139,7 +139,7 @@ Simple MNIST - + diff --git a/latest/index.html b/latest/index.html index dcce4493..3bac4ccc 100644 --- a/latest/index.html +++ b/latest/index.html @@ -147,7 +147,7 @@ Home - + @@ -167,10 +167,10 @@ Flux
-Flux is a machine learning library, implemented in Julia. In a nutshell, it simply lets you run normal Julia code on a backend like TensorFlow. It also provides many conveniences for doing deep learning. +Flux is a library for machine learning, implemented in Julia. In a nutshell, it simply lets you run normal Julia code on a backend like TensorFlow. It also provides many conveniences for doing deep learning.
-This gives you great flexibility. You can use a convenient Keras-like API if you want something simple, but you can also drop down to straight mathematics, or build your own abstractions. You can even use Flux's utilities (like optimisers) with a completely different backend (like
+Flux is very flexible. You can use a convenient Keras-like API if you want something simple, but you can also drop down to straight mathematics, or build your own abstractions. You can even use Flux's utilities (like optimisers) with a completely different backend (like
Knet
diff --git a/latest/internals.html b/latest/internals.html
index 3851d056..a233ed71 100644
--- a/latest/internals.html
+++ b/latest/internals.html
@@ -136,7 +136,7 @@ Internals
-
+
diff --git a/latest/models/basics.html b/latest/models/basics.html
index 86d8914b..b5b48d78 100644
--- a/latest/models/basics.html
+++ b/latest/models/basics.html
@@ -170,7 +170,7 @@ Model Building Basics
-
+
@@ -347,7 +347,7 @@ Dressed like a model
We noted above that a model is a function with trainable parameters. Normal functions like
exp
- are actually models too, that happen to have 0 parameters. Flux doesn't care, and anywhere that you use one, you can use the other. For example,
+ are actually models too – they just happen to have 0 parameters. Flux doesn't care, and anywhere that you use one, you can use the other. For example,
Chain
will happily work with regular functions: