l1

dragon.vm.tensorflow.keras.regularizers.l1(l=0.01)[source]

Create a L1 regularizer.

The L1 regularizer is defined as:

\[loss_{reg} = loss + \alpha|w| \]
Parameters:
  • l (float, optional, default=0.01) – The value of \(\alpha\).
Returns:

dragon.vm.tensorflow.keras.regularizers.Regularizer – The regularizer.