Struct NormalizedKernel 

pub struct NormalizedKernel { /* private fields */ }

Wrapper that creates a normalized version of any kernel.

The normalized kernel computes K_norm(x,y) = K(x,y) / sqrt(K(x,x) * K(y,y)) ensuring that K_norm(x,x) = 1.0 for all x.

Implementations

impl NormalizedKernel

pub fn new(base_kernel: Box<dyn Kernel>) -> Self

Create a new normalized kernel wrapper

Examples

use tensorlogic_sklears_kernels::{LinearKernel, NormalizedKernel, Kernel};

let linear = Box::new(LinearKernel::new());
let normalized = NormalizedKernel::new(linear);

let x = vec![1.0, 2.0, 3.0];
let y = vec![4.0, 5.0, 6.0];
let sim = normalized.compute(&x, &y).unwrap();

// Self-similarity should be 1.0
let self_sim = normalized.compute(&x, &x).unwrap();
assert!((self_sim - 1.0).abs() < 1e-10);

Trait Implementations

impl Kernel for NormalizedKernel

fn compute(&self, x: &[f64], y: &[f64]) -> Result<f64>

Compute kernel value between two inputs.

fn name(&self) -> &str

Get kernel name for identification.

fn compute_matrix(&self, inputs: &[Vec<f64>]) -> Result<Vec<Vec<f64>>>

Compute kernel matrix for a set of inputs.

fn is_psd(&self) -> bool

Check if kernel is positive semi-definite.