Struct DKLConfig 

pub struct DKLConfig {
    pub feature_layers: Vec<usize>,
    pub n_components: usize,
    pub activation: Activation,
    pub gamma: Float,
    pub learning_rate: Float,
}

Deep Kernel Learning combines deep neural networks with kernel methods

This approach uses a deep neural network to learn a feature representation, then applies a kernel method in the learned feature space.

Mathematical Background

Deep Kernel Learning defines a composite kernel: k(x, x’) = k_base(φ(x; θ), φ(x’; θ)) where:

• φ(·; θ) is a deep neural network with parameters θ
• k_base is a base kernel (e.g., RBF)

Examples

use sklears_kernel_approximation::deep_learning_kernels::{DeepKernelLearning, DKLConfig};
use scirs2_core::ndarray::array;
use sklears_core::traits::{Fit, Transform};

let config = DKLConfig {
    feature_layers: vec![10, 20, 10],
    n_components: 50,
    ..Default::default()
};

let dkl = DeepKernelLearning::new(config);
let X = array![[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]];
let fitted = dkl.fit(&X, &()).unwrap();
let features = fitted.transform(&X).unwrap();
assert_eq!(features.shape(), &[3, 50]);

Fields

feature_layers: Vec<usize>

Sizes of feature extraction layers

n_components: usize

Number of random Fourier features for final kernel

activation: Activation

Activation function for feature layers

gamma: Float

Bandwidth for final RBF kernel

learning_rate: Float

Learning rate for feature learning (currently not trainable, uses random features)

Trait Implementations

impl Clone for DKLConfig

fn clone(&self) -> DKLConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DKLConfig

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

Formats the value using the given formatter.

impl Default for DKLConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for DKLConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for DKLConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.