Struct vikos::teacher::GradientDescent

pub struct GradientDescent {
    pub learning_rate: f64,
}

Gradient descent

Simplest possible implementation of gradient descent with fixed learning rate

Fields

learning_rate: f64

Defines how fast the coefficents of the trained Model will change

Trait Implementations

impl<M> Teacher<M> for GradientDescent where M: Model

type Training = ()

Contains state which changes during the training, but is not part of the expertise

fn new_training(&self, _: &M)

Creates an instance holding all mutable state of the algorithm

fn teach_event<Y, C>(&self, _training: &mut (), model: &mut M, cost: &C, features: &M::Input, truth: Y) where C: Cost<Y>, Y: Copy

Changes models coefficents so they minimize the cost function (hopefully)