emel/ml/neural_network

A collection of connected neurons, that looks like a biological brain. Each connection, can transmit a signal from one neuron to another.

Functions

pub fn classifier(
  data: List(#(List(Float), String)),
  hidden_layers: List(Int),
  learning_rate: Float,
  error_threshold: Float,
  max_iterations: Int,
) -> fn(List(Float)) -> String

Returns the function that classifies a point by using the Neural Network Framework.

Data = [
  {[0.8, 0.0, 0.0], "x"},
  {[0.0, 0.9, 0.0], "y"},
  {[0.0, 0.0, 0.8], "z"}
],
HiddenLayers = [4],
LearningRate = 0.01,
ErrorThreshold = 0.1,
MaxIterations = 1000,
F = emel@ml@neural_network:classifier(Data, HiddenLayers, LearningRate, ErrorThreshold, MaxIterations),
F([0.0, 0.8, 0.0]).
% "y"
Search Document