neural network concept and example

ann

An artificial neural network is an interconnected group of nodes, akin to the vast network of neurons in a brain. Here, each circular node represents an artificial neuron and an arrow represents a connection from the output of one neuron to the input of another.

Example: character recornization

Make the system learn by 10 sample of 1-10 digits
While learning we will collect pixel positions for each digits.
Like if are learning digit '1'. So for each of 10 test, we will collect pixel position. We can store normalized mean value for digit 1 now.

Suppose now new digit comes and we want to identify it. So we will calculate the euclidian distance for input digit to all database learned digits. For which every euclidian distance is least, that is predicted digit.

Input digit - Imput neural
normalization and euclidian function - hidden layer
out digit - output neuron