Trait juice::solver::ISolver[][src]

pub trait ISolver<SolverB, B> where
    B: IBackend + LayerOps<f32>,
    SolverB: IBackend + SolverOps<f32>, 
{ fn compute_update(
        &mut self,
        param: &SolverConfig,
        network: &mut Layer<B>,
        iter: usize
fn backend(&self) -> &SolverB; fn init(&mut self, net: &Layer<B>) { ... } }
Expand description

Implementation of a specific Solver.

See [Solvers][1] [1]: ../solvers/index.html

Required methods

Update the weights of the net with part of the gradient.

The second phase of backpropagation learning. Calculates the gradient update that should be applied to the network, and then applies that gradient to the network, changing its weights.

Used by step to optimize the network.

Returns the backend used by the solver.

Provided methods

Initialize the solver, setting up any network related data.

Trait Implementations

Formats the value using the given formatter. Read more