Documentation

Trainer is a typeclass for all trainer types - a trainer will take in an instance of itself, a network, a list of training data, and return a new network trained on the data. class Trainer a where fit :: (Floating b) => a -> Network b -> [TrainingData b] -> Network b

A BackpropTrainer performs simple backpropagation on a neural network. It can be used as the basis for more complex trainers.

A CostFunction is used for evaluating a network's performance on a given input

A CostFunction' (derivative) is used in backPropagation

A selection function for performing gradient descent

The quadratic cost function (1/2) * sum (y - a) ^ 2

The derivative of the quadratic cost function sum (y - a)

The minibatch function becomes a Selection when partially applied with the minibatch size

If we want to train the network online

Perform backpropagation on a single training data instance.

The inputs function performs a similar task to outputs, but returns a list of vectors of unactivated inputs

The outputs function scans over each layer of the network and stores the activated results

The deltas function returns a list of layer deltas.

Declare the BackpropTrainer to be an instance of Trainer. instance (Floating a) => Trainer (BackpropTrainer a) where

Use the cost function to determine the error of a network