The Error Function
Explore the concept of error functions used in deep learning to measure prediction accuracy. Learn how mean squared error applies to regression, while cross-entropy suits classification. Understand the formulas and reasons for choosing these loss functions to optimize your models effectively.
We'll cover the following...
The accuracy of the predicted output can be calculated by comparing it with the target output. This accounts for computing the error.
Error function (or loss)
Mean squared error (MSE)
The error is the difference between the actual value and the predicted value. We want this error value to be minimum to get the best possible function. This error equation is given by:
📝 Note: Since a negative error would not make sense, square the error function to force the raw error to be positive by multiplying it by itself.
-
...