Empirical risk minimization

Empirical risk minimization (ERM) is a principle in statistical learning theory which defines a family of learning algorithms and is used to give theoretical bounds on the performance of learning algorithms.
Contents ...

Empirical Risk Minimization A parameter estimation heuristic that seeks parameter values that minimize the "risk" or "loss" that the model incurs on the training data.

The formulation uses the Structural Risk Minimization (SRM) principle, which has been shown to be superior, [4], to traditional Empirical Risk Minimization (ERM) principle, used by conventional neural networks.

See also: Classification, Loss function, Machine learning, Regression, Distribution