Neural network for Iris recognition

This neural network represents a first approach to Machine Learning.

Data set description

The dataset used is the "Iris Plants Database" (http://archive.ics.uci.edu/ml/datasets/Iris), created by R.A. Fisher.

The data set contains 3 classes of 50 instances each (150 total instances), where each class refers to a type of iris plant.

Attributes informations:

1. sepal length in cm

2. sepal width in cm

3. petal length in cm

4. petal width in cm

5. class:

   -- Iris Setosa

   -- Iris Versicolour

   -- Iris Virginica

Neural network evaluation

The neural network reaches:

1. test accuracy: 98%

2. test loss: 0.33