Sequence of AutoEncoders to be stacked.
All weights of layers
Compute output of neural network with given input (without reconstruction) If drop-out is used, to average drop-out effect, we need to multiply output by presence probability.
Compute output of neural network with given input (without reconstruction) If drop-out is used, to average drop-out effect, we need to multiply output by presence probability.
an input vector
output of the vector
All accumulated delta weights of layers
All accumulated delta weights of layers
all accumulated delta weights
Sequence of AutoEncoders to be stacked.
Sugar: Forward computation for training.
Sugar: Forward computation for training. Calls apply(x)
input matrix
output matrix
Sugar: Forward computation for validation.
Sugar: Forward computation for validation. Calls apply(x)
input matrix
output matrix
Serialize network to JSON
Serialize network to JSON
JsObject of this network
Backpropagation algorithm
Backpropagation algorithm
backpropagated error from error function
Network: Stack of autoencoders.