In this article you’ll learn about Neural Networks. What is a neural network? The human brain can be seen as a neural network —an interconnected web of neurons .

In Machine Learning, there exist an algorithm known as an Aritifical Neural Network. They mimic biological neural networks. A network always starts with a single unit: the perceptron.

Related course:

A perceptron

A single perceptron is the basis of a neural network.

A perceptron has:

  • one or more inputs
  • a bias
  • an activation function
  • a single output

a perceptron, basis of neural network

A perceptron receives inputs. It then multiplies them by some weight. Then they are send into an activation function to produce an output. We also add a bias value, it allows you to shift the activation function.

Network Layers

A neural network is created by adding layers of perceptrons together: the multi-layer perceptron (MLP) algorithm.

We’ll have several layers:

the input layertakes your data
the hidden layerany layers between the input and output are called hidden layers
output layersthe output results

Graphically that looks like this (source: Wikipedia):

neural network