Struct ExponentialCurriculum 

pub struct ExponentialCurriculum {
    pub start_percentage: f64,
    pub growth_rate: f64,
}

Exponential curriculum: exponentially increase sample percentage.

Uses an exponential schedule to quickly ramp up the number of training samples.

Fields

start_percentage: f64

Initial percentage of samples.

growth_rate: f64

Exponential growth rate (higher = faster growth).

Implementations

impl ExponentialCurriculum

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

Create a new exponential curriculum.

Arguments

• start_percentage - Initial percentage of samples
• growth_rate - Growth rate (e.g., 2.0 for doubling)

Trait Implementations

impl Clone for ExponentialCurriculum

fn clone(&self) -> ExponentialCurriculum

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl CurriculumStrategy for ExponentialCurriculum

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 ExponentialCurriculum

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

Formats the value using the given formatter.

impl Default for ExponentialCurriculum

fn default() -> Self

Returns the “default value” for a type.