Flux.jl/docs/src/models/layers.md

## Basic Layers

These core layers form the foundation of almost all neural networks.

```@docs
Chain
Dense
Conv2D
```

## Recurrent Layers

Much like the core layers above, but can be used to process sequence data (as well as other kinds of structured data).

```@docs
RNN
LSTM
Flux.Recur
```

## Activation Functions

Non-linearities that go between layers of your model. Most of these functions are defined in [NNlib](https://github.com/FluxML/NNlib.jl) but are available by default in Flux.

Note that, unless otherwise stated, activation functions operate on scalars. To apply them to an array you can call `σ.(xs)`, `relu.(xs)` and so on.

```@docs
σ
relu
leakyrelu
elu
swish
```

## Normalisation & Regularisation

These layers don't affect the structure of the network but may improve training times or reduce overfitting.

```@docs
Flux.testmode!
BatchNorm
Dropout
LayerNorm
```
-												minor wording

											
										
										
											2017-10-23 12:07:07 +00:00
+								## Basic Layers
-												layer docs

											
										
										
											2017-09-08 21:52:41 +00:00
-												model layers note

											
										
										
											2017-10-18 11:31:06 +00:00
+								These core layers form the foundation of almost all neural networks.
-												layer docs

											
										
										
											2017-09-08 21:52:41 +00:00
+								```@docs
 								Chain
 								Dense
-												conv docs

											
										
										
											2017-12-18 18:05:48 +00:00
+								Conv2D
-												layer docs

											
										
										
											2017-09-08 21:52:41 +00:00
+								```
-												nnlib docs

											
										
										
											2017-10-18 10:09:33 +00:00
-												minor wording

											
										
										
											2017-10-23 12:07:07 +00:00
+								## Recurrent Layers
-												rnn docs

											
										
										
											2017-10-18 14:30:05 +00:00
 								Much like the core layers above, but can be used to process sequence data (as well as other kinds of structured data).
 								```@docs
 								RNN
 								LSTM
-												syntax highlighting

											
										
										
											2017-10-18 14:44:06 +00:00
+								Flux.Recur
-												rnn docs

											
										
										
											2017-10-18 14:30:05 +00:00
+								```
-												nnlib docs

											
										
										
											2017-10-18 10:09:33 +00:00
+								## Activation Functions
 								Non-linearities that go between layers of your model. Most of these functions are defined in [NNlib](https://github.com/FluxML/NNlib.jl) but are available by default in Flux.
 								Note that, unless otherwise stated, activation functions operate on scalars. To apply them to an array you can call `σ.(xs)`, `relu.(xs)` and so on.
 								```@docs
 								σ
 								relu
 								leakyrelu
 								elu
 								swish
 								```
-												reorganise

											
										
										
											2017-10-26 10:46:12 +00:00
 								## Normalisation & Regularisation
 								These layers don't affect the structure of the network but may improve training times or reduce overfitting.
 								```@docs
-												doc fixes

											
										
										
											2017-11-21 11:29:02 +00:00
+								Flux.testmode!
-												batchnorm: update docs

											
										
										
											2017-10-30 05:33:01 +00:00
+								BatchNorm
-												reorganise

											
										
										
											2017-10-26 10:46:12 +00:00
+								Dropout
-												LayerNorm tweaks

											
										
										
											2017-10-23 11:53:07 +00:00
+								LayerNorm
-												reorganise

											
										
										
											2017-10-26 10:46:12 +00:00
+								```