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:

diff --git a/latest/models/debugging.html b/latest/models/debugging.html index 70fe7fa9..b336cd53 100644 --- a/latest/models/debugging.html +++ b/latest/models/debugging.html @@ -139,7 +139,7 @@ Debugging - + diff --git a/latest/models/recurrent.html b/latest/models/recurrent.html index 0754e3aa..1d242451 100644 --- a/latest/models/recurrent.html +++ b/latest/models/recurrent.html @@ -139,7 +139,7 @@ Recurrence - + diff --git a/latest/models/templates.html b/latest/models/templates.html index 1a971647..f1cd92dc 100644 --- a/latest/models/templates.html +++ b/latest/models/templates.html @@ -155,7 +155,7 @@ Model Templates - + diff --git a/latest/search_index.js b/latest/search_index.js index 46b2593e..b50c3096 100644 --- a/latest/search_index.js +++ b/latest/search_index.js @@ -13,7 +13,7 @@ var documenterSearchIndex = {"docs": [ "page": "Home", "title": "Flux", "category": "section", - "text": "... Initialising Photon Beams ...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.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 Knet) or mix and match approaches.Note that Flux is in alpha. Many things work but the API is still in a state of... well, it might change.Note: If you're using Julia v0.5 please see this version of the docs instead." + "text": "... Initialising Photon Beams ...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.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) or mix and match approaches.Note that Flux is in alpha. Many things work but the API is still in a state of... well, it might change.Note: If you're using Julia v0.5 please see this version of the docs instead." }, { @@ -93,7 +93,7 @@ var documenterSearchIndex = {"docs": [ "page": "Model Building Basics", "title": "Dressed like a model", "category": "section", - "text": "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, Chain will happily work with regular functions:foo = Chain(exp, sum, log)\nfoo([1,2,3]) == 3.408 == log(sum(exp([1,2,3])))" + "text": "We noted above that a model is a function with trainable parameters. Normal functions like exp 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:foo = Chain(exp, sum, log)\nfoo([1,2,3]) == 3.408 == log(sum(exp([1,2,3])))" }, {