Skip to main content

Regularizer

tensorlogic_train

Trait Regularizer 

Source 
pub trait Regularizer {
    // Required methods
    fn compute_penalty(
        &self,
        parameters: &HashMap<String, Array<f64, Ix2>>,
    ) -> TrainResult<f64>;
    fn compute_gradient(
        &self,
        parameters: &HashMap<String, Array<f64, Ix2>>,
    ) -> TrainResult<HashMap<String, Array<f64, Ix2>>>;
}
Expand description

Trait for regularization strategies.

Required Methods§

Source

fn compute_penalty( &self, parameters: &HashMap<String, Array<f64, Ix2>>, ) -> TrainResult<f64>

Compute the regularization penalty for given parameters.

§Arguments
  • parameters - Model parameters to regularize
§Returns

The regularization penalty value

Source

fn compute_gradient( &self, parameters: &HashMap<String, Array<f64, Ix2>>, ) -> TrainResult<HashMap<String, Array<f64, Ix2>>>

Compute the gradient of the regularization penalty.

§Arguments
  • parameters - Model parameters
§Returns

Gradients of the regularization penalty for each parameter

Dyn Compatibility§

This trait is dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementations on Foreign Types§

Source§

impl Regularizer for Box<dyn RegularizerClone>

Source§

fn compute_penalty( &self, parameters: &HashMap<String, Array<f64, Ix2>>, ) -> TrainResult<f64>

Source§

fn compute_gradient( &self, parameters: &HashMap<String, Array<f64, Ix2>>, ) -> TrainResult<HashMap<String, Array<f64, Ix2>>>

Implementors§