Struct Neuron 

pub struct Neuron<T: Float> {
    pub sum: T,
    pub value: T,
    pub activation_steepness: T,
    pub activation_function: ActivationFunction,
    pub connections: Vec<Connection<T>>,
    pub is_bias: bool,
}

Represents a single neuron in the neural network

Fields

sum: T

The sum of inputs multiplied by weights

value: T

The output value after applying the activation function

activation_steepness: T

The steepness parameter for the activation function

activation_function: ActivationFunction

The activation function to use

connections: Vec<Connection<T>>

Incoming connections to this neuron

is_bias: bool

Whether this is a bias neuron

Implementations

impl<T: Float> Neuron<T>

pub fn new( activation_function: ActivationFunction, activation_steepness: T, ) -> Self

Creates a new neuron with the specified activation function and steepness

Arguments

• activation_function - The activation function to use
• activation_steepness - The steepness parameter for the activation function

Example

use ruv_fann::{Neuron, ActivationFunction};

let neuron = Neuron::<f32>::new(ActivationFunction::Sigmoid, 1.0);
assert_eq!(neuron.activation_function, ActivationFunction::Sigmoid);

pub fn new_bias() -> Self

Creates a new bias neuron with a constant output value of 1.0

pub fn add_connection(&mut self, from_neuron: usize, weight: T)

Adds a connection from another neuron to this neuron

Arguments

• from_neuron - Index of the source neuron
• weight - Initial weight of the connection

pub fn clear_connections(&mut self)

Clears all connections

pub fn reset(&mut self)

Resets the neuron’s sum and value to zero (except for bias neurons which maintain value = 1.0)

pub fn calculate(&mut self, inputs: &[T])

Calculates the neuron’s output based on inputs and weights

Arguments

• inputs - Values from neurons in the previous layer

pub fn set_value(&mut self, value: T)

Sets the neuron’s output value directly (used for input neurons)

pub fn get_connection_weight(&self, index: usize) -> Option<T>

Gets the weight of a specific connection by index

pub fn set_connection_weight( &mut self, index: usize, weight: T, ) -> Result<(), &'static str>

Sets the weight of a specific connection by index

Trait Implementations

impl<T: Clone + Float> Clone for Neuron<T>

fn clone(&self) -> Neuron<T>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<T: Debug + Float> Debug for Neuron<T>

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

Formats the value using the given formatter.

impl<'de, T> Deserialize<'de> for Neuron<T>

where T: Deserialize<'de> + Float,

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl<T: Float> PartialEq for Neuron<T>

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl<T> Serialize for Neuron<T>

where T: Serialize + Float,

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.