Probability and Statistics, Understanding probability and statistics concepts for machine learning

Basic probability concepts

Why probability?

A neural network is a semantic network, where a set of input/output units (“neurons”) are connected to each other, and these connections are weighted relative to the importance or strength of the link between one neuron and the next. Such networks are called feedforward neural networks.
Neural Network Let's extend above neural network to classify species of iris flowers. we will use sklearn to load iris dataset, the dataset looks like

sepal length (cm)sepal width (cm)petal length (cm)petal width (cm)
5.13.51.40.2
4.93.01.40.2
4.73.21.30.2
4.63.11.50.2
5.00.60.40.2

The target names are 'setosa', 'versicolor', 'virginica'. The above netowrk will classify the flower species into three possible species

0setosa 1versicolor2virginica0\quad \rightarrow \quad setosa\\ \quad \ 1\quad \rightarrow \quad versicolor\\ \quad 2\quad \rightarrow \quad virginica