Understanding Neural Networks in 5 Minutes

Now, computers can identify objects in images from different angles, talk to you, and play games with you. But it begs the question: just how does it all work??

You probably know that everything above has to do with artificial intelligence (AI), but in this article we are going to go more specific into a part of AI: neural networks. They make decisions, whether it’s returning search results, giving you personalized content, or translating text.

So, how do neural networks make decisions? Like us, they need input data and process the data to output something. The rest of this article is focused on this data processing that happens between input and output.

The fundamental building blocks of neural networks are nodes and connections between these nodes. Resembling the neurons and synapses of a human brain, nodes and their connections are structured to analyze input and form a meaningful output.

Before we get into the specific structures, let’s quickly talk about what a node and a connection actually do. In the simplest case, nodes just store a single number, but just remembering data isn’t helpful; it’s connections between nodes that modify and transfer what’s stored in the nodes, so data can be analyzed. These connections range from just multiplying the data by a designated number to plugging the number into a nonlinear function.

Then, how can we actually use nodes and connections to make them useful in a neural network?

In AI, there are many different types of neural networks with unique structures, but for this introduction, we will discuss a specific type: fully connected neural networks, which are often used in combination with other neural networks in recognizing images.

In fully connected neural networks, nodes are lined up into columns, which are called layers. As the name suggests, every node in every layer except for the last is connected to every node in the next layer. In this neural network, the number of layers and the number of nodes in each layer may vary; however, the property of being “fully connected” doesn’t change.