Machine Learning Terms

Loss Function

By Nadirhan ┼×ahin

Function that is used to evaluate the performance of a model and guide the training process.

Loss Functions (aka Cost Functions) show the error between what value your model predicts and what the value actually is. Since these functions are generally differentiable (with some exceptions i.e. Hinge Loss), we can apply a Gradient Descent to find the least error. Some common ones are:

For Regression Models:

For Classification Models:

  • Binary Cross Entropy Loss
  • Categorical Cross Entropy Loss