Struct rusty_machine::learning::nnet::MSECriterion
[−]
[src]
pub struct MSECriterion { /* fields omitted */ }
The mean squared error criterion.
Uses the Linear activation function and the mean squared error.
Methods
impl MSECriterion
[src]
fn new(regularization: Regularization<f64>) -> Self
Constructs a new BCECriterion with the given regularization.
Examples
use rusty_machine::learning::nnet::MSECriterion; use rusty_machine::learning::toolkit::regularization::Regularization; // Create a new MSE criterion with L2 regularization of 0.3. let criterion = MSECriterion::new(Regularization::L2(0.3f64));
Trait Implementations
impl Clone for MSECriterion
[src]
fn clone(&self) -> MSECriterion
Returns a copy of the value. Read more
fn clone_from(&mut self, source: &Self)
1.0.0
Performs copy-assignment from source
. Read more
impl Copy for MSECriterion
[src]
impl Debug for MSECriterion
[src]
impl Criterion for MSECriterion
[src]
type ActFunc = Linear
The activation function for the criterion.
type Cost = MeanSqError
The cost function for the criterion.
fn regularization(&self) -> Regularization<f64>
Returns the regularization for this criterion. Read more
fn activate(&self, mat: Matrix<f64>) -> Matrix<f64>
The activation function applied to a matrix.
fn grad_activ(&self, mat: Matrix<f64>) -> Matrix<f64>
The gradient of the activation function applied to a matrix.
fn cost(&self, outputs: &Matrix<f64>, targets: &Matrix<f64>) -> f64
The cost function. Read more
fn cost_grad(&self, outputs: &Matrix<f64>, targets: &Matrix<f64>) -> Matrix<f64>
The gradient of the cost function. Read more
fn is_regularized(&self) -> bool
Checks if the current criterion includes regularization. Read more
fn reg_cost(&self, reg_weights: MatrixSlice<f64>) -> f64
Returns the regularization cost for the criterion. Read more
fn reg_cost_grad(&self, reg_weights: MatrixSlice<f64>) -> Matrix<f64>
Returns the regularization gradient for the criterion. Read more
impl Default for MSECriterion
[src]
Creates an MSE Criterion without any regularization.