To specify the architecture of a neural network with all layers connected sequentially, create an array of layers directly. To specify the architecture of a network where layers can have multiple inputs or outputs, use a LayerGraph object. Use the following functions to create different layer types.
Input Layers:
| FUNCTION |
DESCRIPTION |
| imageInputLayer |
Inputs images to a network
Applies data normalization
. |
| sequenceInputLayer |
Inputs sequence data to a network.
|
Learnable Layers:
| FUNCTION |
DESCRIPTION |
| convolution2dLayer |
Applies sliding filters to the input.
It convolves the input by moving the filters along the input vertically and horizontally and computing the dot product of the weights and the input, and then adding a bias term.
|
| transposedConv2dLayer |
It upsamples feature maps.
|
| fullyConnectedLayer |
Multiplies the input by a weight matrix and then adds a bias vector
. |
| lstmLayer |
It is a recurrent neural network (RNN) layer that enables support for time series and sequence data in a network.
It performs additive interactions, which can help improve gradient flow over long sequences during training.
They are best suited for learning long-term dependencies
. |
Activation Layers:
| FUNCTION |
DESCRIPTION |
| reluLayer |
It performs a threshold operation to each element of the input, where any value less than zero is set to zero.
|
| leakyReluLayer |
It performs a simple threshold operation, where any input value less than zero is multiplied by a fixed scalar
|
| clippedReluLayer |
It performs a simple threshold operation, where any input value less than zero is set to zero.
Any value above the clipping ceiling is set to that clipping ceiling.
|
Normalization and Dropout Layers:
| FUNCTION |
DESCRIPTION |
| batchNormalizationLayer |
It normalizes each input channel across a mini-batch.
The layer first normalizes the activations of each channel by subtracting the mini-batch mean and dividing by the mini-batch standard deviation.
Then, the layer shifts the input by a learnable offset and scales it by a learnable scale factor.
Use batch normalization layers between convolutional layers and nonlinearities, such as ReLU layers, to speed up training of convolutional neural networks and reduce the sensitivity to network initialization.
|
| crossChannelNormalizationLayer |
It carries out channel-wise normalization.
|
| dropoutLayer |
It randomly sets input elements to zero with a given probability.
|
Pooling Layers:
| FUNCTION |
DESCRIPTION |
| averagePooling2dLayer |
It performs down sampling by dividing the input into rectangular pooling regions and computing the average values of each region.
|
| maxPooling2dLayer |
It performs down sampling by dividing the input into rectangular pooling regions, and computing the maximum of each region.
|
| maxUnpooling2dLayer |
It unpools the output of a max pooling layer.
|
Combination Layers:
| FUNCTION |
DESCRIPTION |
| additionLayer |
It adds multiple inputs element-wise.
Specify the number of inputs to the layer when you create it.
The inputs have names ‘in1’, ‘in2’, …, ‘inN’, where N is the number of inputs.
Use the input names when connecting or disconnecting the layer to other layers using connectLayers or disconnectLayers.
All inputs to an addition layer must have the same dimension.
|
| depthConcatenationLayer |
It takes multiple inputs that have the same height and width.
It concatenates them along the third dimension.
|
Output Layers:
| FUNCTION |
DESCRIPTION |
| softmaxLayer |
It applies a softmax function to the input.
|
| classificationLayer |
It holds the name of the loss function the software uses for training the network for multiclass classification
. |
| regressionLayer |
It holds the name of the loss function the software uses for training the network for regression, and the response names.
|
