Struct MatchingNetworks 

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

Matching Networks for Few-Shot Learning

Matching Networks use attention mechanisms to match query samples to support samples. The key idea is to learn a function that can map a small labeled support set and an unlabeled example to its label.

The method uses an attention mechanism to compare the query sample with all support examples and produces a weighted combination of their labels.

Implementations

impl MatchingNetworks<Untrained>

pub fn new() -> Self

Create a new MatchingNetworks instance

pub fn embedding_dim(self, embedding_dim: usize) -> Self

Set the embedding dimensionality

pub fn lstm_layers(self, lstm_layers: usize) -> Self

Set the number of LSTM layers

pub fn attention_layers(self, attention_layers: usize) -> Self

Set the number of attention layers

pub fn learning_rate(self, learning_rate: f64) -> Self

Set the learning rate

pub fn n_episodes(self, n_episodes: usize) -> Self

Set the number of training episodes

pub fn use_full_context(self, use_full_context: bool) -> Self

Set whether to use full context embeddings

pub fn temperature(self, temperature: f64) -> Self

Set the temperature parameter

Trait Implementations

impl<S: Clone> Clone for MatchingNetworks<S>

fn clone(&self) -> MatchingNetworks<S>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<S: Debug> Debug for MatchingNetworks<S>

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

Formats the value using the given formatter.

impl Default for MatchingNetworks<Untrained>

fn default() -> Self

Returns the “default value” for a type.

impl Estimator for MatchingNetworks<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]>>, ArrayBase<ViewRepr<&i32>, Dim<[usize; 1]>>> for MatchingNetworks<Untrained>

type Fitted = MatchingNetworks<MatchingNetworksTrained>

The fitted model type

fn fit( self, X: &ArrayView2<'_, Float>, y: &ArrayView1<'_, i32>, ) -> 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

impl Predict<ArrayBase<ViewRepr<&f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<i32>, Dim<[usize; 1]>>> for MatchingNetworks<MatchingNetworksTrained>

fn predict(&self, X: &ArrayView2<'_, Float>) -> SklResult<Array1<i32>>

Make predictions on the provided data

fn predict_with_uncertainty( &self, x: &X, ) -> Result<(Output, UncertaintyMeasure), SklearsError>

Make predictions with confidence intervals

impl PredictProba<ArrayBase<ViewRepr<&f64>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>> for MatchingNetworks<MatchingNetworksTrained>

fn predict_proba(&self, X: &ArrayView2<'_, Float>) -> SklResult<Array2<f64>>

Predict class probabilities