Uses of Package
org.deeplearning4j.nn.conf.layers

Autoencoder layer.

A neural network layer.

2D deconvolution layer configuration
Deconvolutions are also known as transpose convolutions or fractionally strided convolutions.

Dense layer: a standard fully connected feed forward layer

Dropout layer.

Deprecated. 

Deprecated. 

A neural network layer.

Local response normalization layer
See section 3.3 of http://www.cs.toronto.edu/~fritz/absps/imagenet.pdf

LossLayer is a flexible output layer that performs a loss function on an input without MLP logic.

A version of OutputLayer for recurrent neural networks.

2D Separable convolution layer configuration.

Subsampling layer also referred to as pooling in convolution neural nets Supports the following pooling types: MAX, AVG, SUM, PNORM

A neural network layer.

2D Convolution layer (for example, spatial convolution over images).

The backward data algorithm to use when ConvolutionLayer.AlgoMode is set to "USER_SPECIFIED".

The forward algorithm to use when ConvolutionLayer.AlgoMode is set to "USER_SPECIFIED".

Embedding layer: feed-forward layer that expects single integers per example as input (class numbers, in range 0 to numClass-1) as input.

Embedding layer for sequences: feed-forward layer that expects fixed-length number (inputLength) of integers/indices per example as input, ranged from 0 to numClasses - 1.

Created by jeffreytang on 7/21/15.

Global pooling layer - used to do pooling over time for RNNs, and 2d pooling for CNNs.

Deprecated. 

Deprecated. 

Parametrized Rectified Linear Unit (PReLU) f(x) = alpha * x for x < 0, f(x) = x for x >= 0 alpha has the same shape as x and is a learned parameter.

1D (temporal) subsampling layer - also known as pooling layer.

3D subsampling / pooling layer for convolutional neural networks Supports max and average pooling modes

Subsampling layer also referred to as pooling in convolution neural nets Supports the following pooling types: MAX, AVG, SUM, PNORM

Upsampling 1D layer
Repeats each step size times along the temporal/sequence axis (dimension 2)
For input shape [minibatch, channels, sequenceLength] output has shape [minibatch, channels, size * sequenceLength]
Example: If input (for a single example, with channels down page, and sequence from left to right) is: [ A1, A2, A3] [ B1, B2, B3] Then output with size = 2 is: [ A1, A1, A2, A2, A3, A3] [ B1, B1, B2, B2, B3, B2]

Upsampling 2D layer
Repeats each value (or rather, set of depth values) in the height and width dimensions by size[0] and size[1] times respectively.

Upsampling 3D layer
Repeats each value (all channel values for each x/y/z location) by size[0], size[1] and size[2]
If input has shape [minibatch, channels, depth, height, width] then output has shape [minibatch, channels, size[0] * depth, size[1] * height, size[2] * width]

Zero padding 1D layer for convolutional neural networks.

Zero padding layer for convolutional neural networks (2D CNNs).

The backward data algorithm to use when ConvolutionLayer.AlgoMode is set to "USER_SPECIFIED".

The forward algorithm to use when ConvolutionLayer.AlgoMode is set to "USER_SPECIFIED".

The backward data algorithm to use when ConvolutionLayer.AlgoMode is set to "USER_SPECIFIED".

The forward algorithm to use when ConvolutionLayer.AlgoMode is set to "USER_SPECIFIED".

Deprecated. 

A neural network layer.

Parametrized Rectified Linear Unit (PReLU) f(x) = alpha * x for x < 0, f(x) = x for x >= 0 alpha has the same shape as x and is a learned parameter.

2D Convolution layer (for example, spatial convolution over images).

2D depth-wise convolution layer configuration.

Space to channels utility layer configuration for convolutional input types.

Upsampling 2D layer
Repeats each value (or rather, set of depth values) in the height and width dimensions by size[0] and size[1] times respectively.

Zero padding 1D layer for convolutional neural networks.

Zero padding layer for convolutional neural networks (2D CNNs).

Dense layer: a standard fully connected feed forward layer

SameDiff version of a 2D locally connected layer.

Pooling type:
MAX: Max pooling - output is the maximum value of the input values
AVG: Average pooling - output is the average value of the input values
SUM: Sum pooling - output is the sum of the input values
PNORM: P-norm pooling

3D subsampling / pooling layer for convolutional neural networks Supports max and average pooling modes

A neural network layer.

A neural network layer.

2D Convolution layer (for example, spatial convolution over images).

Subsampling layer also referred to as pooling in convolution neural nets Supports the following pooling types: MAX, AVG, SUM, PNORM