Loss Functions

Every loss function in GradCore-Tensor, including their forward computations, backward passes, and when to use each one.

📄️Loss Functions

A loss function measures how wrong your model is. Training is the process of making it less wrong, one gradient at a time. Choosing the right loss function is not optional — using MSE for a classification problem is like using a ruler to measure temperature.

📄️Reduction Modes

Reduction modes control whether a loss function returns a per-element tensor or collapses to a scalar. Every loss function in GradCore-Tensor accepts a Reduction argument.