Trait gad::net_ext::DiffNet [−][src]
pub trait DiffNet<T>: Net<Graph1, Output = Value<T>> where
T: Number,
Self::Weights: WeightOps<T>, { fn apply_gradient_step(
&mut self,
lambda: T,
batch: Vec<Self::Input>
) -> Result<T> { ... } }
Extension trait when the algebra is crate::Graph1
and the output is a scalar.
Provided methods
fn apply_gradient_step(
&mut self,
lambda: T,
batch: Vec<Self::Input>
) -> Result<T>
[src]
&mut self,
lambda: T,
batch: Vec<Self::Input>
) -> Result<T>
Apply a “mini-batch” gradient step.
Self::Output = Value<T>
is a scalar value representing the error.lambda
is expected to be negative for loss minimization.
Implementors
Loading content...