Struct ContinualLearningPipeline 

pub struct ContinualLearningPipeline<S = Untrained> { /* private fields */ }

Continual learning pipeline

Implementations

impl ContinualLearningPipeline<Untrained>

pub fn new( base_estimator: Box<dyn PipelinePredictor>, strategy: ContinualLearningStrategy, ) -> Self

Create a new continual learning pipeline

pub fn elastic_weight_consolidation( base_estimator: Box<dyn PipelinePredictor>, lambda: f64, fisher_samples: usize, ) -> Self

Create EWC pipeline

pub fn experience_replay( base_estimator: Box<dyn PipelinePredictor>, buffer_size: usize, replay_batch_size: usize, replay_frequency: usize, ) -> Self

Create experience replay pipeline

pub fn learning_without_forgetting( base_estimator: Box<dyn PipelinePredictor>, temperature: f64, distillation_weight: f64, ) -> Self

Create Learning without Forgetting pipeline

pub fn set_current_task(self, task_id: String) -> Self

Set current task ID

impl ContinualLearningPipeline<ContinualLearningPipelineTrained>

pub fn predict(&self, x: &ArrayView2<'_, Float>) -> SklResult<Array1<f64>>

Predict using the fitted continual learning model

pub fn learn_task(&mut self, task: Task) -> SklResult<()>

Learn a new task

pub fn evaluate_forgetting( &self, previous_tasks: &[Task], ) -> SklResult<HashMap<String, f64>>

Evaluate catastrophic forgetting

pub fn memory_statistics(&self) -> HashMap<String, f64>

Get memory buffer statistics

pub fn learned_tasks(&self) -> &[String]

Get learned tasks

pub fn task_performance(&self) -> &HashMap<String, HashMap<String, f64>>

Get task performance

pub fn importance_weights(&self) -> &HashMap<String, f64>

Get importance weights

Trait Implementations

impl<S: Debug> Debug for ContinualLearningPipeline<S>

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

Formats the value using the given formatter.

impl Estimator for ContinualLearningPipeline<Untrained>

type Config = ()

Configuration type for the estimator

type Error = SklearsError

Error type for the estimator

type Float = f64

The numeric type used by this estimator

fn config(&self) -> &Self::Config

Get estimator configuration

fn validate_config(&self) -> Result<(), SklearsError>

Validate estimator configuration with detailed error context

fn check_compatibility( &self, n_samples: usize, n_features: usize, ) -> Result<(), SklearsError>

Check if estimator is compatible with given data dimensions

fn metadata(&self) -> EstimatorMetadata

Get estimator metadata

impl Fit<ArrayBase<ViewRepr<&f64>, Dim<[usize; 2]>>, Option<&ArrayBase<ViewRepr<&f64>, Dim<[usize; 1]>>>> for ContinualLearningPipeline<Untrained>

type Fitted = ContinualLearningPipeline<ContinualLearningPipelineTrained>

The fitted model type

fn fit( self, x: &ArrayView2<'_, Float>, y: &Option<&ArrayView1<'_, Float>>, ) -> SklResult<Self::Fitted>

Fit the model to the provided data with validation

fn fit_with_validation( self, x: &X, y: &Y, _x_val: Option<&X>, _y_val: Option<&Y>, ) -> Result<(Self::Fitted, FitMetrics), SklearsError>

where Self: Sized,

Fit with custom validation and early stopping