# neupy.algorithms.WeightDecay

class neupy.algorithms.WeightDecay[source]

Weight decay algorithm penalizes large weights. Also known as L2-regularization.

Parameters: decay_rate : float Controls training penalties during the parameter updates. The larger the value the stronger effect regularization has during the training. Defaults to 0.1. It works with any algorithm based on the backpropagation.

Examples

>>> from neupy import algorithms