Trait rusty_machine::learning::nnet::Criterion [−] [src]

pub trait Criterion {
    type ActFunc: ActivationFunc;
    type Cost: CostFunc<Matrix<f64>>;
    fn activate(&self, mat: Matrix<f64>) -> Matrix<f64> { ... }
    fn grad_activ(&self, mat: Matrix<f64>) -> Matrix<f64> { ... }
    fn cost(&self, outputs: &Matrix<f64>, targets: &Matrix<f64>) -> f64 { ... }
    fn cost_grad(&self, outputs: &Matrix<f64>, targets: &Matrix<f64>) -> Matrix<f64> { ... }
    fn regularization(&self) -> Regularization<f64> { ... }
    fn is_regularized(&self) -> bool { ... }
    fn reg_cost(&self, reg_weights: MatrixSlice<f64>) -> f64 { ... }
    fn reg_cost_grad(&self, reg_weights: MatrixSlice<f64>) -> Matrix<f64> { ... }
}

Criterion for Neural Networks

Specifies an activation function and a cost function.

Associated Types

The activation function for the criterion.

The cost function for the criterion.

Provided Methods

The activation function applied to a matrix.

The gradient of the activation function applied to a matrix.

The cost function.

Returns a scalar cost.

The gradient of the cost function.

Returns a matrix of cost gradients.

Returns the regularization for this criterion.

Will return Regularization::None by default.

Checks if the current criterion includes regularization.

Will return false by default.

Returns the regularization cost for the criterion.

Will return 0 by default.

This method will not be invoked by the neural network if there is explicitly no regularization.

Returns the regularization gradient for the criterion.

Will return a matrix of zeros by default.

This method will not be invoked by the neural network if there is explicitly no regularization.

Implementors