Enum cogent::Cost

pub enum Cost {
    Quadratic,
    Crossentropy,
}

Defines cost function of a neural network.

Variants

Quadratic

Quadratic cost function.

$ C(w,b)=\frac{1}{2n}\sum_{x} ||y(x)-a(x) ||^2 $

Crossentropy

Crossentropy cost function.

$ C(w,b) = -\frac{1}{n} \sum_{x} (y(x) \ln{(a(x))} + (1-y(x)) \ln{(1-a(x))}) $

Implementations

impl Cost

pub fn run(&self, y: &Array<f32>, a: &Array<f32>) -> f32

Runs cost functions.

y: Target out, a: Actual out.

pub fn derivative(&self, y: &Array<f32>, a: &Array<f32>) -> Array<f32>

Derivative w.r.t. layer output (∂C/∂a).

y: Target out, a: Actual out.

Trait Implementations

impl<'de> Deserialize<'de> for Cost

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error> where
    __D: Deserializer<'de>, 

Deserialize this value from the given Serde deserializer.

impl Serialize for Cost

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error> where
    __S: Serializer, 

Serialize this value into the given Serde serializer.