Struct rusty_machine::learning::nnet::BCECriterion [] [src]

pub struct BCECriterion { /* fields omitted */ }

The binary cross entropy criterion.

Uses the Sigmoid activation function and the cross entropy error.

Methods

impl BCECriterion
[src]

Constructs a new BCECriterion with the given regularization.

Examples

use rusty_machine::learning::nnet::BCECriterion;
use rusty_machine::learning::toolkit::regularization::Regularization;

// Create a new BCE criterion with L2 regularization of 0.3.
let criterion = BCECriterion::new(Regularization::L2(0.3f64));

Trait Implementations

impl Clone for BCECriterion
[src]

Returns a copy of the value. Read more

Performs copy-assignment from source. Read more

impl Copy for BCECriterion
[src]

impl Debug for BCECriterion
[src]

Formats the value using the given formatter.

impl Criterion for BCECriterion
[src]

The activation function for the criterion.

The cost function for the criterion.

Returns the regularization for this criterion. Read more

The activation function applied to a matrix.

The gradient of the activation function applied to a matrix.

The cost function. Read more

The gradient of the cost function. Read more

Checks if the current criterion includes regularization. Read more

Returns the regularization cost for the criterion. Read more

Returns the regularization gradient for the criterion. Read more

impl Default for BCECriterion
[src]

Creates an MSE Criterion without any regularization.

Returns the "default value" for a type. Read more