Struct SelfPacedCurriculum 

pub struct SelfPacedCurriculum {
    pub lambda: f64,
    pub threshold: f64,
}

Self-paced learning: model determines its own learning pace.

Adaptively selects samples based on current model performance, prioritizing samples the model is ready to learn from.

Fields

lambda: f64

Age parameter controlling pace (higher = more aggressive).

threshold: f64

Threshold for sample selection.

Implementations

impl SelfPacedCurriculum

pub fn new(lambda: f64, threshold: f64) -> TrainResult<Self>

Create a new self-paced curriculum.

Arguments

• lambda - Age parameter (controls learning pace)
• threshold - Selection threshold

Trait Implementations

impl Clone for SelfPacedCurriculum

fn clone(&self) -> SelfPacedCurriculum

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl CurriculumStrategy for SelfPacedCurriculum

fn select_samples( &self, _epoch: usize, _total_epochs: usize, difficulties: &ArrayView1<'_, f64>, ) -> TrainResult<Vec<usize>>

Get the subset of samples to use for the current training step.

fn compute_difficulty( &self, _data: &Array2<f64>, labels: &Array2<f64>, predictions: Option<&Array2<f64>>, ) -> TrainResult<Array1<f64>>

Compute difficulty scores for training samples.

impl Debug for SelfPacedCurriculum

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for SelfPacedCurriculum

fn default() -> Self

Returns the “default value” for a type.