Struct RestrictedBoltzmannMachine 

pub struct RestrictedBoltzmannMachine {
    pub n_visible: usize,
    pub n_hidden: usize,
    pub learning_rate: f64,
    pub n_epochs: usize,
    pub batch_size: usize,
    pub n_gibbs_steps: usize,
    pub random_state: Option<u64>,
    /* private fields */
}

Restricted Boltzmann Machine (RBM) component

An RBM is a two-layer neural network with visible and hidden units that can learn probability distributions over its inputs.

Fields

n_visible: usize

n_visible

n_hidden: usize

n_hidden

learning_rate: f64

learning_rate

n_epochs: usize

n_epochs

batch_size: usize

batch_size

n_gibbs_steps: usize

n_gibbs_steps

random_state: Option<u64>

random_state

Implementations

impl RestrictedBoltzmannMachine

pub fn new(n_visible: usize, n_hidden: usize) -> Result<Self>

pub fn learning_rate(self, learning_rate: f64) -> Result<Self>

pub fn n_epochs(self, n_epochs: usize) -> Result<Self>

pub fn batch_size(self, batch_size: usize) -> Result<Self>

pub fn n_gibbs_steps(self, n_gibbs_steps: usize) -> Result<Self>

pub fn random_state(self, random_state: u64) -> Self

pub fn fit(&mut self, data: &ArrayView2<'_, f64>) -> Result<()>

pub fn transform(&self, data: &ArrayView2<'_, f64>) -> Result<Array2<f64>>

pub fn reconstruct(&self, data: &ArrayView2<'_, f64>) -> Result<Array2<f64>>

Trait Implementations

impl Clone for RestrictedBoltzmannMachine

fn clone(&self) -> RestrictedBoltzmannMachine

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RestrictedBoltzmannMachine

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

Formats the value using the given formatter.