emel v0.3.0 Emel.Ml.NeuralNetwork View Source
A collection of connected neurons, that looks like a biological brain. Each connection, can transmit a signal from one neuron to another.
Link to this section Summary
Functions
Returns the function that classifies an item (or a list of items) by using the Neural Network Framework
Link to this section Functions
Link to this function
classifier(dataset, continuous_attributes, class, hidden_layers, learning_rate \\ 0.0001, err_thres \\ 0.1, max_iter \\ 10000)
View Source
Returns the function that classifies an item (or a list of items) by using the Neural Network Framework.
Examples
iex> f = Emel.Ml.NeuralNetwork.classifier(
...> [%{a: 0, b: 0, exclusive_or: false},
...> %{a: 0, b: 1, exclusive_or: true},
...> %{a: 1, b: 0, exclusive_or: true},
...> %{a: 1, b: 1, exclusive_or: false}],
...> [:a, :b], # features
...> :exclusive_or, # class
...> [2], # single hidden layer with two neurons
...> 0.5, # learning rate
...> 0.01, # error threshold
...> 10000 # maximum number of iterations
...> )
...> f.([%{a: 0, b: 0},
...> %{a: 0, b: 1},
...> %{a: 1, b: 0},
...> %{a: 1, b: 1}])
[false, true, true, false]