Struct HomeostaticNeuralClusterer 

pub struct HomeostaticNeuralClusterer { /* private fields */ }

Advanced homeostatic plasticity for neuromorphic spatial learning

This clusterer implements homeostatic plasticity mechanisms that maintain stable neural activity levels while adapting to input patterns. It includes intrinsic plasticity, synaptic scaling, and multi-timescale adaptation.

Features

• Homeostatic neurons with intrinsic plasticity
• Synaptic scaling for stability
• Multi-timescale adaptation (fast, medium, slow)
• Metaplasticity for adaptive learning rates
• Target firing rate maintenance

Example

use scirs2_core::ndarray::Array2;
use scirs2_spatial::neuromorphic::algorithms::HomeostaticNeuralClusterer;

let points = Array2::from_shape_vec((4, 2), vec![
    0.0, 0.0, 1.0, 0.0, 0.0, 1.0, 1.0, 1.0
]).unwrap();

let mut clusterer = HomeostaticNeuralClusterer::new(2, 2)
    .with_homeostatic_params(0.1, 1000.0);
let assignments = clusterer.fit(&points.view(), 50).unwrap();

Implementations

impl HomeostaticNeuralClusterer

pub fn new(num_clusters: usize, input_dim: usize) -> Self

Create new homeostatic neural clusterer

Arguments

• num_clusters - Number of clusters to discover
• input_dim - Number of input dimensions

Returns

A new HomeostaticNeuralClusterer with default parameters

pub fn with_homeostatic_params( self, target_firing_rate: f64, homeostatic_tau: f64, ) -> Self

Configure homeostatic parameters

Arguments

• target_firing_rate - Target firing rate for neurons
• homeostatic_tau - Time constant for homeostatic adaptation

pub fn fit( &mut self, points: &ArrayView2<'_, f64>, epochs: usize, ) -> SpatialResult<Array1<usize>>

Fit homeostatic clustering model

Trains the network using homeostatic plasticity mechanisms to discover stable cluster representations while maintaining target activity levels.

Arguments

• points - Input spatial points (n_points × n_dims)
• epochs - Number of training epochs

Returns

Cluster assignments for each input point

pub fn get_cluster_centers(&self) -> Array2<f64>

Get cluster centers (weights)

pub fn num_clusters(&self) -> usize

Get number of clusters

pub fn neuron_firing_rates(&self) -> Vec<f64>

Get neuron firing rates

pub fn current_learning_rate(&self) -> f64

Get current learning rate

Trait Implementations

impl Clone for HomeostaticNeuralClusterer

fn clone(&self) -> HomeostaticNeuralClusterer

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for HomeostaticNeuralClusterer

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

Formats the value using the given formatter.