Welcome to our Support Center
UpdatedJuly 23, 2025

L1L2

Description

Define L1L2 regularizer. This mode combines both L1 and L2 penalties, allowing a trade-off between sparsity and weight decay. It is useful when you want to benefit from both effects in a single model. When selected explicitly, both l1 and l2 coefficients are user-defined. Type : polymorphic.

 

 

Input parameters

 

 Parameters : cluster,

l1 : float, L1 regularization factor.
l2 : float, L2 regularization factor.

 

Output parameters

 

Regularizer : cluster, this cluster defines the regularization strategy used to constrain model weights.

enum : enum, an enumeration indicating the regularizer type (e.g., None, L1, L2, etc.). If enum is set to CustomRegularizer, the custom class will be used. Otherwise, the selected regularizer will be applied using default settings.
 Class : object, a custom regularizer class instance.

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install Deep Learning library to run it).
Table of Contents