Struct CompetenceCurriculum 

pub struct CompetenceCurriculum {
    pub initial_competence: f64,
    pub growth_rate: f64,
    pub max_competence: f64,
}

Competence-based curriculum: adapts to model’s current competence level.

Gradually increases difficulty based on model’s mastery of easier samples.

Fields

initial_competence: f64

Initial competence level (0.0 to 1.0).

growth_rate: f64

Competence growth rate per epoch.

max_competence: f64

Maximum competence level.

Implementations

impl CompetenceCurriculum

pub fn new(initial_competence: f64, growth_rate: f64) -> TrainResult<Self>

Create a new competence-based curriculum.

Arguments

• initial_competence - Starting competence level
• growth_rate - How fast competence grows per epoch

Trait Implementations

impl Clone for CompetenceCurriculum

fn clone(&self) -> CompetenceCurriculum

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl CurriculumStrategy for CompetenceCurriculum

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 CompetenceCurriculum

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

Formats the value using the given formatter.

impl Default for CompetenceCurriculum

fn default() -> Self

Returns the “default value” for a type.