Struct rusty_machine::learning::nnet::BaseNeuralNet

pub struct BaseNeuralNet<'a, T: Criterion> { /* fields omitted */ }

Base Neural Network struct

This struct cannot be instantianated and is used internally only.

Trait Implementations

impl<'a, T: Debug + Criterion> Debug for BaseNeuralNet<'a, T>

fn fmt(&self, __arg_0: &mut Formatter) -> Result

Formats the value using the given formatter.

impl<'a, T: Criterion> Optimizable for BaseNeuralNet<'a, T>

Compute the gradient of the Neural Network using the back propagation algorithm.

type Inputs = Matrix<f64>

The input data type to the model.

type Targets = Matrix<f64>

The target data type to the model.

fn compute_grad(&self,
                params: &[f64],
                inputs: &Matrix<f64>,
                targets: &Matrix<f64>)
                -> (f64, Vec<f64>)

Compute the gradient of the neural network.