Struct FullyConnected 

pub struct FullyConnected { /* private fields */ }

Fully connected (dense) wiring structure.

Every neuron connects to every other neuron (and optionally to itself). This provides a baseline comparison for NCP’s sparse connectivity.

When to Use

• Baseline comparison: Compare NCP performance against dense networks
• Maximum expressiveness: When sparsity is not a concern
• Debugging: Simpler structure for testing

Sparsity

FullyConnected has no sparsity - the adjacency matrix is fully populated. For a network with N units, this means N² internal synapses (or N²-N without self-connections).

Example

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

// Create a fully-connected wiring with 32 neurons, 8 outputs
let mut wiring = FullyConnected::new(
    32,        // units (total neurons)
    Some(8),   // output_dim (motor neurons)
    42,        // seed for reproducibility
    true,      // self_connections allowed
);

// Build with input dimension
wiring.build(16);

// Check connectivity
println!("Total synapses: {}", wiring.synapse_count());  // 32*32 = 1024
println!("Sensory synapses: {}", wiring.sensory_synapse_count());  // 16*32 = 512

Comparison with NCP

Aspect	FullyConnected	NCP
Synapses	O(N²)	O(N) to O(N log N)
Interpretability	Low	High
Parameters	More	Fewer
Structure	Single layer	4-layer biological

Implementations

impl FullyConnected

pub fn new( units: usize, output_dim: Option<usize>, erev_init_seed: u64, self_connections: bool, ) -> Self

pub fn get_full_config(&self) -> WiringConfig

Get configuration for serialization

pub fn from_config(config: WiringConfig) -> Self

Trait Implementations

impl Clone for FullyConnected

fn clone(&self) -> FullyConnected

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FullyConnected

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

Formats the value using the given formatter.

impl Wiring for FullyConnected

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 build(&mut self, input_dim: usize)

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

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 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 is_built(&self) -> bool

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

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

Returns the type of a neuron by its ID.

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).