Neural Networks Simply Explained

With Video Explanation | Data Series | Episode 13.1

In this episode, we look to explain neural networks by going through how to construct a simple neural network step-by-step.

Overview

A neural network is a popular and adaptive machine learning algorithm that was inspired by the structure of the human brain.

A neuron has many inputs and a single or multiple outputs:

Constructing a Neural Network

Step 1: Build the structure

A neural network is made up of neurons or nodes that process data and produce an output, represented as a circle. The number of nodes in a neural network is pre-set by the user.

A neural network has the same core structure of an input layer, hidden layer or layers and an output layer.

To explain the maths behind a neural network we look at the simplest form of a neural network with n inputs and one output. This is known as a perceptron:

Step 2: Set weights and biases