Network.Neuron

Documentation

data Neuron a

Using this structure allows users of the library to create their own neurons by creating two functions - an activation function and its derivative - and packaging them up into a neuron type.

Constructors

Neuron

Fields

activation :: ActivationFunction a

activation' :: ActivationFunction' a

type ActivationFunction a = a -> a

type ActivationFunction' a = a -> a

sigmoidNeuron :: Floating a => Neuron a

Our provided neuron types: sigmoid, tanh, reclu

tanhNeuron :: Floating a => Neuron a

recluNeuron :: Floating a => Neuron a

sigmoid :: Floating a => a -> a

The sigmoid activation function, a standard activation function defined on the range (0, 1).

sigmoid' :: Floating a => a -> a

The derivative of the sigmoid function conveniently can be computed in terms of the sigmoid function.

tanh :: Floating a => a -> a

tanh' :: Floating a => a -> a

The hyperbolic tangent activation function is provided in Prelude. Here we provide the derivative. As with the sigmoid function, the derivative of tanh can be computed in terms of tanh.

reclu :: Floating a => a -> a

The rectified linear activation function. This is a more "biologically accurate" activation function that still retains differentiability.

reclu' :: Floating a => a -> a

The derivative of the rectified linear activation function is just the sigmoid.