Struct EneCode 

pub struct EneCode {
    pub neuron_id: Vec<String>,
    pub topology: Vec<TopologyGene>,
    pub neuronal_props: NeuronalPropertiesGene,
    pub meta_learning: MetaLearningGene,
}

EneCode encapsulates the genetic blueprint for constructing an entire neural network.

This struct holds all the information required to instantiate a neural network with distinct neurons, synaptic connections, and meta-learning parameters. It consists of a collection of genes that provide the blueprint for each individual neuron’s topology, its neuronal properties, and meta-learning rules.

Fields

• neuron_id - A vector containing the unique identifiers for each neuron in the genome. These IDs are used to find the associated topology gene for each neuron.

• topology - A list of TopologyGene structs that describe the synaptic connections, neuron types, and other topological features for each neuron in the network.

• neuronal_props - An instance of NeuronalPropertiesGene that provides global neuronal properties like time constants, homeostatic forces, and activation function scaling factors.

• meta_learning - An instance of MetaLearningGene that provides meta-learning parameters such as learning rate and learning thresholds for synaptic adjustments.

Example Usage

use evo_rl::enecode::EneCode;
use evo_rl::enecode::TopologyGene;
use evo_rl::enecode::NeuronalPropertiesGene;
use evo_rl::enecode::MetaLearningGene;
use evo_rl::enecode::NeuronType;

// Initialization (example)
let genome = EneCode::new_from_genome (
    vec![
        TopologyGene {
            innovation_number: Arc::from("N1"),
            pin: NeuronType::In,
            inputs: HashMap::new(),
            genetic_bias: 0.1,
            active: true
        },
        // ... more TopologyGene
    ],
    NeuronalPropertiesGene {
        innovation_number: Arc::from("NP01"),
        tau: 0.9,
        homeostatic_force: 0.1,
        tanh_alpha: 2.0,
    },
    MetaLearningGene {
        innovation_number: Arc::from("MTL01"),
        learning_rate: 0.01,
        learning_threshold: 0.5,
    });

Fields

neuron_id: Vec<String>

topology: Vec<TopologyGene>

neuronal_props: NeuronalPropertiesGene

meta_learning: MetaLearningGene

Implementations

impl EneCode

pub fn new( num_inputs: usize, num_hidden: usize, num_outputs: usize, module: Option<&str>, ) -> Self

Constructor function for basic genome with defined number of inputs/outputs

pub fn generate_new_topology( input_size: usize, output_size: usize, num_hidden: usize, ) -> Vec<TopologyGene>

Generates an appropriate Vec for a given number of inputs and outputs and hidden neurons. Default is a fully connected FF layer.

pub fn new_from_genome( topology: Vec<TopologyGene>, neuronal_props: NeuronalPropertiesGene, meta_learning: MetaLearningGene, ) -> Self

Constructor function for EneCode based on established genome, puts things into correct order based on NeuronType and innovation number

pub fn topology_gene(&self, neuron_id: &str) -> &TopologyGene

Fetches the topology gene corresponding to a given neuron ID.

Arguments

• neuron_id - The unique identifier for the neuron.

Returns

A reference to the TopologyGene associated with the neuron ID.

pub fn recombine<R: Rng>( &self, rng: &mut R, other_genome: &EneCode, ) -> Result<EneCode, RecombinationError>

Performs genetic recombination during mating

Arguments

• rng - thread_rng
• other_genome - the enecode of the partner to recombine with

Returns

A Result<EneCode, RecombinationError>

Trait Implementations

impl Clone for EneCode

fn clone(&self) -> EneCode

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EneCode

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EneCode

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<&NeuralNetwork> for EneCode

Creates genome from neural network after recombination and mutation

fn from(network: &NeuralNetwork) -> Self

Converts to this type from the input type.

impl IntoPy<Py<PyAny>> for EneCode

fn into_py(self, py: Python<'_>) -> PyObject

Performs the conversion.

impl PartialEq for EneCode

fn eq(&self, other: &EneCode) -> 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 PyClass for EneCode

type Frozen = False

Whether the pyclass is frozen.

impl PyClassImpl for EneCode

const IS_BASETYPE: bool = false

#[pyclass(subclass)]

const IS_SUBCLASS: bool = false

#[pyclass(extends=…)]

const IS_MAPPING: bool = false

#[pyclass(mapping)]

const IS_SEQUENCE: bool = false

#[pyclass(sequence)]

type BaseType = PyAny

Base class

type ThreadChecker = SendablePyClass<EneCode>

This handles following two situations:

type PyClassMutability = <<PyAny as PyClassBaseType>::PyClassMutability as PyClassMutability>::MutableChild

Immutable or mutable

type Dict = PyClassDummySlot

Specify this class has #[pyclass(dict)] or not.

type WeakRef = PyClassDummySlot

Specify this class has #[pyclass(weakref)] or not.

type BaseNativeType = PyAny

The closest native ancestor. This is PyAny by default, and when you declare #[pyclass(extends=PyDict)], it’s PyDict.

fn items_iter() -> PyClassItemsIter

fn doc(py: Python<'_>) -> PyResult<&'static CStr>

Rendered class doc

fn lazy_type_object() -> &'static LazyTypeObject<Self>

fn dict_offset() -> Option<isize>

fn weaklist_offset() -> Option<isize>

impl<'a, 'py> PyFunctionArgument<'a, 'py> for &'a EneCode

type Holder = Option<PyRef<'py, EneCode>>

fn extract(obj: &'py PyAny, holder: &'a mut Self::Holder) -> PyResult<Self>

impl<'a, 'py> PyFunctionArgument<'a, 'py> for &'a mut EneCode

type Holder = Option<PyRefMut<'py, EneCode>>

fn extract(obj: &'py PyAny, holder: &'a mut Self::Holder) -> PyResult<Self>

impl PyTypeInfo for EneCode

const NAME: &'static str = "EneCode"

Class name.

const MODULE: Option<&'static str> = ::core::option::Option::None

Module name, if any.

type AsRefTarget = PyCell<EneCode>

Utility type to make Py::as_ref work.

fn type_object_raw(py: Python<'_>) -> *mut PyTypeObject

Returns the PyTypeObject instance for this type.

fn type_object(py: Python<'_>) -> &PyType

Returns the safe abstraction over the type object.

fn is_type_of(object: &PyAny) -> bool

Checks if object is an instance of this type or a subclass of this type.

fn is_exact_type_of(object: &PyAny) -> bool

Checks if object is an instance of this type.

impl Serialize for EneCode

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl ToPyObject for EneCode

fn to_object(&self, py: Python<'_>) -> PyObject

Converts self into a Python object.

impl TryFrom<&PathBuf> for EneCode

type Error = Error

The type returned in the event of a conversion error.

fn try_from(checkpoint: &PathBuf) -> Result<Self, Self::Error>

Performs the conversion.

impl StructuralPartialEq for EneCode