Struct KnnDecoder 

pub struct KnnDecoder { /* private fields */ }

Simple KNN decoder using stored labeled embeddings.

Classifies a query embedding by majority vote among its k nearest neighbors in Euclidean distance.

Implementations

impl KnnDecoder

pub fn new(k: usize) -> Self

Create a new KNN decoder with the given k (number of neighbors).

pub fn train(&mut self, embeddings: Vec<(NeuralEmbedding, CognitiveState)>)

Load labeled training data into the decoder.

pub fn predict(&self, embedding: &NeuralEmbedding) -> CognitiveState

Predict the cognitive state for a query embedding using majority vote.

Returns CognitiveState::Unknown if no training data is available.

pub fn predict_with_confidence( &self, embedding: &NeuralEmbedding, ) -> (CognitiveState, f64)

Predict the cognitive state with a confidence score in [0, 1].

Confidence is the fraction of the k nearest neighbors that agree on the winning state.

pub fn num_samples(&self) -> usize

Number of stored labeled embeddings.

Trait Implementations

impl StateDecoder for KnnDecoder

fn decode(&self, embedding: &NeuralEmbedding) -> Result<CognitiveState>

Decode the most likely cognitive state from an embedding.

fn decode_with_confidence( &self, embedding: &NeuralEmbedding, ) -> Result<(CognitiveState, f64)>

Decode with a confidence score in [0, 1].