Num::NN::NetworkInfo(T)

This should always be initialized with an empty array of layers that can be tapped and yielded by Network creation

Adds an Adam optimizer to the Network

Convolution layer for a neural network

Arguments

• n : Int32 - Number of filters to apply
• kh : Int32 - Filter height
• kw : Int32 - Filter width

Adds a dropout layer for a neural network

Arguments

• prob : Float - Probability of a neuron being dropped out

Adds an ELU layer to the network

Adds a Flattening layer to a neural network

Adds an input layer to a Network. This is simply a wrapper around the input Tensor, in order to allow layers further along in the network to infer input shapes

Arguments

• shape : Array(Int) - Shape of input data

Adds a Leaky ReLU layer to a network.

Add a linear layer to the Network. Since activation functions are just treated as additional layers, this simply requires the dimensions of the transformation.

Dimensions should be NUM_FEATURES x NUM_OUTPUTS, so if the data set is 100x10, with 200 neurons in the hidden layers, the dimensions of the layer would be 10, 100, the 200 will be handled by dynamically.

Arguments

• output_size : Int - The number of outputs in the linear layer

Examples

net = Num::NN::Network.new(ctx) do
  linear 2, 3
end

Maxpool layer for a neural network

Arguments

• kernel : Tuple(Int, Int) - Kernel height and width
• padding : Tuple(Int, Int)` - Padding height and width
• stride : Tuple(Int, Int)` - Stride height and width

Uses Mean Squared Error to compute the loss for the Network

Examples

net = Num::NN::Network.new(ctx) do
  linear 2, 3
  sigmoid
  linear 3, 1
  sgd 0.7
  mse_loss
end

Add a ReLU layer to the Network. Activation functions are handled the same way as other layers, but do not change the dimensions of the input

Examples

net = Num::NN::Network.new(ctx) do
  linear 2, 3
  relu
end

Add an SGD optimizer to the Network.

Arguments

• learning_rate : Float64 - Learning rate for all layers in the Network

Examples

net = Num::NN::Network.new(ctx) do
  linear 2, 3
  sigmoid
  linear 3, 1
  sgd 0.7
end

Add a Sigmoid layer to the Network. Activation functions are handled the same way as other layers, but do not change the dimensions of the input

Examples

net = Num::NN::Network.new(ctx) do
  linear 2, 3
  sigmoid
end

Uses Sigmoid Cross Entropy to compute the loss for the Network

Examples

net = Num::NN::Network.new(ctx) do
  linear 2, 3
  sigmoid
  linear 3, 1
  sgd 0.7
  sigmoid_cross_entropy_loss
end

Specifies Softmax Cross Entropy as the method of loss to be used with the Network