Struct AutoNCP 

pub struct AutoNCP { /* private fields */ }

Automatic NCP configuration with simplified parameters.

AutoNCP is the recommended way to create NCP wirings. It automatically calculates layer sizes and connectivity based on just a few high-level parameters.

Simplified Interface

Instead of specifying 7 parameters like NCP, you only need 4:

Parameter	Description
units	Total number of neurons (hidden state size)
output_size	Number of motor neurons (output dimension)
sparsity_level	Fraction of connections to remove (0.0 - 0.9)
seed	Random seed for reproducibility

How Auto-Configuration Works

Given your parameters, AutoNCP:

1. Allocates neurons: units - output_size split 60/40 between inter/command
2. Sets connectivity: Based on density = 1.0 - sparsity_level
   • sensory_fanout = inter_neurons × density
   • inter_fanout = command_neurons × density
   • motor_fanin = command_neurons × density
   • recurrent_command_synapses = command_neurons × density × 2

Example

use ncps::wirings::{AutoNCP, Wiring};

// Create with automatic configuration
let mut wiring = AutoNCP::new(
    32,    // units: total neurons
    8,     // output_size: motor neurons
    0.5,   // sparsity_level: 50% connections removed
    42,    // seed
);

wiring.build(16);  // 16 input features

// Check auto-calculated structure
assert_eq!(wiring.units(), 32);
assert_eq!(wiring.output_dim(), Some(8));
assert_eq!(wiring.num_layers(), 3);  // inter, command, motor

Sparsity Level Guide

Sparsity	Effect	Use Case
0.0	Dense connections	Maximum expressiveness
0.3-0.5	Moderate sparsity	Recommended starting point
0.7-0.9	Very sparse	Edge deployment, interpretability

Constraints

• output_size < units - 2 (need at least 2 neurons for inter + command)
• sparsity_level must be in [0.0, 0.9]

Panics

use ncps::wirings::AutoNCP;

// Panics: output_size too large
let wiring = AutoNCP::new(10, 9, 0.5, 42);

use ncps::wirings::AutoNCP;

// Panics: sparsity_level out of range
let wiring = AutoNCP::new(32, 8, 0.95, 42);

Implementations

impl AutoNCP

pub fn new( units: usize, output_size: usize, sparsity_level: f64, seed: u64, ) -> Self

Trait Implementations

impl Clone for AutoNCP

fn clone(&self) -> AutoNCP

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AutoNCP

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

Formats the value using the given formatter.

impl Wiring for AutoNCP

fn units(&self) -> usize

Returns the total number of neurons (hidden units) in this wiring.

fn input_dim(&self) -> Option<usize>

Returns the input dimension (number of input features), or None if not yet built.

fn output_dim(&self) -> Option<usize>

Returns the output dimension (number of motor neurons).

fn num_layers(&self) -> usize

Returns the number of logical layers in this wiring.

fn get_neurons_of_layer(&self, layer_id: usize) -> Vec<usize>

Returns the neuron IDs belonging to a specific layer.

fn get_type_of_neuron(&self, neuron_id: usize) -> &'static str

Returns the type of a neuron by its ID.

fn build(&mut self, input_dim: usize)

Builds the wiring by setting the input dimension and creating sensory connections.

fn is_built(&self) -> bool

Returns true if the wiring has been built (input dimension is set).

fn adjacency_matrix(&self) -> &Array2<i32>

Returns the internal adjacency matrix representing neuron-to-neuron synapses.

fn sensory_adjacency_matrix(&self) -> Option<&Array2<i32>>

Returns the sensory adjacency matrix (input-to-neuron connections).

fn add_synapse(&mut self, src: usize, dest: usize, polarity: i32)

Adds or modifies an internal synapse between two neurons.

fn add_sensory_synapse(&mut self, src: usize, dest: usize, polarity: i32)

Adds or modifies a sensory synapse from an input feature to a neuron.

fn get_config(&self) -> WiringConfig

Creates a serializable configuration for this wiring.

fn erev_initializer(&self) -> Array2<i32>

Returns the reversal potential initializer (same as adjacency matrix).

fn sensory_erev_initializer(&self) -> Option<Array2<i32>>

Returns the sensory reversal potential initializer.

fn synapse_count(&self) -> usize

Returns the total number of internal synapses (non-zero entries in adjacency matrix).

fn sensory_synapse_count(&self) -> usize

Returns the total number of sensory synapses (input-to-neuron connections).

fn input_required(&self) -> bool

Returns true if this wiring requires external input (has sensory connections).