Struct PopulationEncoder 

pub struct PopulationEncoder { /* private fields */ }

Encodes a single analog value across a population of neurons

Each neuron in the population is “tuned” to a specific preferred value within the input range. The neuron fires based on a Gaussian-like tuning curve centered on its preferred value. This creates a distributed representation where multiple neurons contribute to encoding a single input value

Mathematical Model

Uses a Gaussian tuning curve to determine each neuron’s firing rate:

preferred_value[i] = range_min + (i / num_neurons) * (range_max - range_min)
distance = |input - preferred_value[i]|
rate = exp(-distance² / (2 * tuning_width²))
spike if random() < rate

When to Use

• Encoding position or continuous values with distributed representation
• When multiple neurons should contribute to representing a single value
• Creating more robust encoding that doesn’t rely on a single neuron

Parameters

• num_neurons: Number of neurons in the population per input channel
• input_range: Tuple of (min, max) input values
• tuning_width: Controls how broadly neurons respond (larger = wider spread)

Examples

use axon_encoder::prelude::*;
let mut enc = PopulationEncoder::try_new(8, (0.0, 1.0), 0.15)?;
// Population encoders take a single scalar in the first channel.
let out = enc.encode(&[0.5]);
assert!(out.spikes.len() <= 8);

Implementations

impl PopulationEncoder

pub fn new( num_neurons: usize, input_range: (f32, f32), tuning_width: f32, ) -> Self

Creates a new PopulationEncoder, panicking if configuration is invalid.

Prefer try_new for typed validation errors.

pub fn try_new( num_neurons: usize, input_range: (f32, f32), tuning_width: f32, ) -> Result<Self, EncoderError>

Creates a new PopulationEncoder, returning an EncoderError for invalid configuration.

pub fn num_neurons(&self) -> usize

Returns the number of neurons in the population

pub fn encode_with_modulators( &mut self, input: &[f32], modulators: &NeuroModulators, gain_curves: &NeuromodulatorGainCurves, ) -> EncodedOutput

Encodes input using neuromodulator-driven gain curves.

Inherent wrapper so callers need not import ModulatedEncoder.

pub fn encode_step_with_modulators( &mut self, input: &[f32], modulators: &NeuroModulators, gain_curves: &NeuromodulatorGainCurves, ) -> EncodedOutput

Step-wise variant of encode_with_modulators.

Trait Implementations

impl Clone for PopulationEncoder

fn clone(&self) -> PopulationEncoder

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PopulationEncoder

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

Formats the value using the given formatter.

impl Encoder for PopulationEncoder

fn encode(&mut self, input: &[f32]) -> EncodedOutput

Encodes a slice of analog values into spike events (batch mode).

fn encode_step(&mut self, input: &[f32]) -> EncodedOutput

Encodes a single step incrementally (streaming mode).

fn reset(&mut self)

Resets the encoder to its initial state

impl ModulatedEncoder for PopulationEncoder

fn encode_with_gains( &mut self, input: &[f32], gains: EncodingGains, ) -> EncodedOutput

Encodes input using already evaluated encoding gains.

fn encode_step_with_gains( &mut self, input: &[f32], gains: EncodingGains, ) -> EncodedOutput

Encodes one streaming step using already evaluated encoding gains.

fn encode_with_modulators( &mut self, input: &[f32], modulators: &NeuroModulators, gain_curves: &NeuromodulatorGainCurves, ) -> EncodedOutput

Encodes input using neuromodulator-driven gain curves.

fn encode_step_with_modulators( &mut self, input: &[f32], modulators: &NeuroModulators, gain_curves: &NeuromodulatorGainCurves, ) -> EncodedOutput

Encodes one streaming step using neuromodulator-driven gain curves.

impl PartialEq for PopulationEncoder

fn eq(&self, other: &PopulationEncoder) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for PopulationEncoder