MeanSquaredLogarithmicError
Description
Computes the mean squared logarithmic error between y_true and y_pred. Type : polymorphic.
Documentation illustration (illustration unavailable in the archive).
Input parameters
Parameters : cluster,
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.
Documentation illustration (illustration unavailable in the archive).
Output parameters
Loss : cluster, this cluster defines the loss function used for model training.
Documentation illustration (illustration unavailable in the archive). 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.
Documentation illustration (illustration unavailable in the archive). Class : object, a custom loss class instance.
Documentation illustration (illustration unavailable in the archive).
Required data
y_pred : array, predicted values. y_true : array, true values.
Use cases
Mean Squared Logarithmic Error (MSLE) is a loss function used in regression problems. It is similar to Mean Squared Error (MSE) but calculates the average of the squares of the differences of the logarithms of the predictions and actual values. This makes MSLE particularly suited to situations where predictions vary widely in magnitude and where proportional errors are more critical than absolute errors.
It is often used when data involves exponential values, such as in forecasting population growth or sales.
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).
Documentation illustration (illustration unavailable in the archive).