pub struct MSECriterion { /* private fields */ }Expand description
The mean squared error criterion.
Uses the Linear activation function and the mean squared error.
Implementations§
Source§impl MSECriterion
impl MSECriterion
Sourcepub fn new(regularization: Regularization<f64>) -> Self
pub 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§
Source§impl Clone for MSECriterion
impl Clone for MSECriterion
Source§fn clone(&self) -> MSECriterion
fn clone(&self) -> MSECriterion
Returns a duplicate of the value. Read more
1.0.0 · Source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source. Read moreSource§impl Criterion for MSECriterion
impl Criterion for MSECriterion
Source§type Cost = MeanSqError
type Cost = MeanSqError
The cost function for the criterion.
Source§fn regularization(&self) -> Regularization<f64>
fn regularization(&self) -> Regularization<f64>
Returns the regularization for this criterion. Read more
Source§fn activate(&self, mat: Matrix<f64>) -> Matrix<f64>
fn activate(&self, mat: Matrix<f64>) -> Matrix<f64>
The activation function applied to a matrix.
Source§fn grad_activ(&self, mat: Matrix<f64>) -> Matrix<f64>
fn grad_activ(&self, mat: Matrix<f64>) -> Matrix<f64>
The gradient of the activation function applied to a matrix.
Source§fn cost(&self, outputs: &Matrix<f64>, targets: &Matrix<f64>) -> f64
fn cost(&self, outputs: &Matrix<f64>, targets: &Matrix<f64>) -> f64
The cost function. Read more
Source§fn cost_grad(&self, outputs: &Matrix<f64>, targets: &Matrix<f64>) -> Matrix<f64>
fn cost_grad(&self, outputs: &Matrix<f64>, targets: &Matrix<f64>) -> Matrix<f64>
The gradient of the cost function. Read more
Source§fn is_regularized(&self) -> bool
fn is_regularized(&self) -> bool
Checks if the current criterion includes regularization. Read more
Source§fn reg_cost(&self, reg_weights: MatrixSlice<'_, f64>) -> f64
fn reg_cost(&self, reg_weights: MatrixSlice<'_, f64>) -> f64
Returns the regularization cost for the criterion. Read more
Source§fn reg_cost_grad(&self, reg_weights: MatrixSlice<'_, f64>) -> Matrix<f64>
fn reg_cost_grad(&self, reg_weights: MatrixSlice<'_, f64>) -> Matrix<f64>
Returns the regularization gradient for the criterion. Read more
Source§impl Debug for MSECriterion
impl Debug for MSECriterion
Source§impl Default for MSECriterion
Creates an MSE Criterion without any regularization.
impl Default for MSECriterion
Creates an MSE Criterion without any regularization.
impl Copy for MSECriterion
Auto Trait Implementations§
impl Freeze for MSECriterion
impl RefUnwindSafe for MSECriterion
impl Send for MSECriterion
impl Sync for MSECriterion
impl Unpin for MSECriterion
impl UnwindSafe for MSECriterion
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more