Neural Networks are a digital imitation of the neurons we see in the human brain.

The world’s first neural network was created by psychologist Frank Rosenblatt and was called the “perceptron”.

This is how it looked.

What you see in the photo are thousands of wires connected to each other.

Rosenblatt wanted to simulate the neurons in our brain using these wires and that is essentially what most neural networks today do!

Expect we do not use thousands of physically connected wires, we use artificial ones that run on our computer’s processor.

The human brain is a collection of neurons connected to each other, in a neural network artificial neurons(the circles) are interconnected and data flows through this network.

Each of these neurons has a numerical value like 1.24,4,5 etc.

The value of a neuron changes to something which is close to what we want each time the data passes through the neural network when we are training it. 

Think of the neurons as dials on a lock, you have to tune every dial to open the lock.

It is almost impossible for a human to tune thousands of dials like these, but a computer certainly can.

Once the dials are well tuned, you have a well trained neural network!

These neural networks can do things from recognizing images to making cars that drive themselves.