Struct RecurrentNeuralNetwork 

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

Recurrent Neural Network for Sequence Prediction

This model can handle various sequence prediction tasks using different cell types (RNN, LSTM, GRU) and output modes.

Examples

use sklears_multioutput::recurrent::{RecurrentNeuralNetwork, CellType, SequenceMode};
use sklears_core::traits::{Predict, Fit};
// Use SciRS2-Core for arrays and random number generation (SciRS2 Policy)

// Example for sequence labeling (many-to-many)
let rnn = RecurrentNeuralNetwork::new()
    .cell_type(CellType::LSTM)
    .hidden_size(50)
    .sequence_mode(SequenceMode::ManyToMany)
    .learning_rate(0.001)
    .max_iter(100);

Implementations

impl RecurrentNeuralNetwork<Untrained>

pub fn new() -> Self

Create a new RecurrentNeuralNetwork instance

pub fn cell_type(self, cell_type: CellType) -> Self

Set the cell type (RNN, LSTM, GRU)

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

Set the hidden layer size

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

Set the number of recurrent layers

pub fn sequence_mode(self, sequence_mode: SequenceMode) -> Self

Set the sequence prediction mode

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

Enable bidirectional processing

pub fn dropout(self, dropout: Float) -> Self

Set dropout rate

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

Set learning rate

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

Set maximum iterations

pub fn tolerance(self, tolerance: Float) -> Self

Set tolerance for convergence

pub fn random_state(self, random_state: Option<u64>) -> Self

Set random state for reproducibility

pub fn alpha(self, alpha: Float) -> Self

Set L2 regularization parameter

impl RecurrentNeuralNetwork<RecurrentNeuralNetworkTrained>

pub fn loss_curve(&self) -> &[Float]

Get the loss curve from training

pub fn n_iter(&self) -> usize

Get training iterations

pub fn cell_type(&self) -> CellType

Get network configuration

pub fn hidden_size(&self) -> usize

Get hidden size

pub fn sequence_mode(&self) -> SequenceMode

Get sequence mode

Trait Implementations

impl<S: Clone> Clone for RecurrentNeuralNetwork<S>

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

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<S: Debug> Debug for RecurrentNeuralNetwork<S>

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

Formats the value using the given formatter.

impl Default for RecurrentNeuralNetwork<Untrained>

fn default() -> Self

Returns the “default value” for a type.

impl Estimator for RecurrentNeuralNetwork<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; 3]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 3]>>> for RecurrentNeuralNetwork<Untrained>

type Fitted = RecurrentNeuralNetwork<RecurrentNeuralNetworkTrained>

The fitted model type

fn fit( self, X: &ArrayView3<'_, Float>, y: &Array3<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

impl Predict<ArrayBase<ViewRepr<&f64>, Dim<[usize; 3]>>, ArrayBase<OwnedRepr<f64>, Dim<[usize; 3]>>> for RecurrentNeuralNetwork<RecurrentNeuralNetworkTrained>

fn predict(&self, X: &ArrayView3<'_, Float>) -> SklResult<Array3<Float>>

Make predictions on the provided data

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

Make predictions with confidence intervals