Struct OjasRule 

pub struct OjasRule {
    pub learning_rate: f64,
    pub w_min: f64,
    pub w_max: f64,
}

Oja’s rule for normalized Hebbian learning.

Oja’s rule prevents unbounded weight growth through normalization.

Δw = η * (y * x - y² * w)

Fields

learning_rate: f64

Learning rate.

w_min: f64

Minimum weight.

w_max: f64

Maximum weight.

Implementations

impl OjasRule

pub fn new() -> Self

Create new Oja’s rule with default parameters.

pub fn update( &mut self, pre_activity: f64, post_activity: f64, current_weight: f64, dt: f64, ) -> f64

Update synaptic weight using Oja’s rule.

Arguments

• pre_activity - Presynaptic activity
• post_activity - Postsynaptic activity
• current_weight - Current synaptic weight
• dt - Time step (ms)

Trait Implementations

impl Clone for OjasRule

fn clone(&self) -> OjasRule

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OjasRule

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

Formats the value using the given formatter.

impl Default for OjasRule

fn default() -> Self

Returns the “default value” for a type.