Welcome to our Support Center
Updated

Huber

Description

Computes the Huber loss between y_true and y_pred.​ Type : polymorphic.

 

 

 

Input parameters

 

Parameters : cluster,

 delta : float, the point where the Huber loss function changes from a quadratic to linear.
reduction : enum, type of reduction to apply to the loss. In almost all cases this should be “Sum over Batch“.
 sample weights : boolean, if enabled, adds an input for weighting each sample individually.

 

Output parameters

 

Loss : cluster, this cluster defines the loss function used for model training.

enum : enum, an enumeration indicating the loss type (e.g., MSE, CrossEntropy, etc.). If enum is set to CustomLoss, the custom class on the right will be used as the loss function. Otherwise, the selected loss will be applied with its default configuration.
 Class : object, a custom loss class instance.

Required data

 y_pred : array, predicted values.
 y_true : array, true values.

Use cases

Huber loss is a loss function commonly used in regression. It combines the advantages of mean squared error (MSE) and mean absolute error (MAE) to create a loss function that is less sensitive to outliers. For small errors, it acts like an MSE, favoring accuracy, and for large errors, it becomes similar to an MAE, reducing sensitivity to extreme values. This characteristic makes it particularly useful in cases where the data contains outliers or significant errors.

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