Struct radiate::models::neat::layers::dense::Dense

pub struct Dense {
    pub inputs: Vec<i32>,
    pub outputs: Vec<i32>,
    pub nodes: HashMap<i32, *mut Neuron>,
    pub edges: HashMap<i32, Edge>,
    pub layer_type: LayerType,
    pub activation: Activation,
}

Fields

inputs: Vec<i32>

outputs: Vec<i32>

nodes: HashMap<i32, *mut Neuron>

edges: HashMap<i32, Edge>

layer_type: LayerType

activation: Activation

Methods

impl Dense

pub fn new(
    num_in: i32,
    num_out: i32,
    layer_type: LayerType,
    activation: Activation,
    counter: &mut Counter
) -> Self

create a new fully connected dense layer. Each input is connected to each output with a randomly generated weight attached to the connection

pub fn add_node(
    &mut self,
    counter: &mut Counter,
    activation: Activation
) -> Option<*mut Neuron>

Add a node to the network by getting a random edge and inserting the new node inbetween that edge's source and destination nodes. The old weight is pushed forward while the new weight is randomly chosen and put between the old source node and the new node

pub fn add_edge(&mut self, counter: &mut Counter) -> Option<Edge>

add a connection to the network. Randomly get a sending node that cannot be an output and a receiving node which is not an input node, the validate that the desired connection can be made. If it can be, make the connection with a weight of .5 in order to minimally impact the network

pub fn see(&self)

Trait Implementations

impl Clone for Dense

Implement clone for the neat neural network in order to facilitate proper crossover and mutation for the network

fn clone(&self) -> Self

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Dense

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

Formats the value using the given formatter.

impl Display for Dense

Simple override of display for neat to debug a little cleaner

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

Formats the value using the given formatter.

impl Drop for Dense

Because the tree is made out of raw mutable pointers, if those pointers are not dropped, there is a severe memory leak, like possibly gigs of ram over only a few generations depending on the size of the generation This drop implementation will recursivley drop all nodes in the tree

fn drop(&mut self)

Executes the destructor for this type.

impl Layer for Dense

fn propagate(&mut self, data: &Vec<f64>) -> Option<Vec<f64>>

Feed a vec of inputs through the network, will panic! if the shapes of the values do not match or if something goes wrong within the feed forward process.

fn backprop(&mut self, error: &Vec<f64>, learning_rate: f64) -> Option<Vec<f64>>

Backpropagation algorithm, transfer the error through the network and change the weights of the edges accordinly, this is pretty straight forward due to the design of the neat graph

fn as_ref_any(&self) -> &dyn Any where
    Self: Sized + 'static, 

fn as_mut_any(&mut self) -> &mut dyn Any where
    Self: Sized + 'static, 

fn shape(&self) -> (usize, usize)

fn max_marker(&self) -> i32

find the max edge innovation number from the network for determing the genetic_structure of this network

impl Mutate<Dense> for Dense where
    Dense: Layer, 

fn mutate(
    child: &mut Dense,
    _: &Dense,
    parent_two: &Dense,
    env: &Arc<RwLock<NeatEnvironment>>,
    crossover_rate: f32
) where
    Self: Sized + Send + Sync, 

fn distance(one: &Dense, two: &Dense, env: &Arc<RwLock<NeatEnvironment>>) -> f64

impl PartialEq<Dense> for Dense

Implement partialeq for neat because if neat itself is to be used as a problem, it must be able to compare one to another

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

This method tests for self and other values to be equal, and is used by ==.

#[must_use] fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl Send for Dense

These must be implemneted for the network or any type to be used within seperate threads. Because implementing the functions themselves is dangerious and unsafe and i'm not smart enough to do that from scratch, these "implmenetaions" will get rid of the error and realistically they don't need to be implemneted for the program to work

impl Sync for Dense