What Is a Neural Network?

They're an important component of AI and machine learning.

An artificial neural network is what is most commonly meant by the neural network. It is a complicated series of interconnected artificial neurons modeled after those in the human brain and used in artificial intelligence to process information, learn, and make predictions.

How Do Neural Networks Work?

A neuron is the human brain's most fundamental cell. A human brain has many billions of neurons, which interact and communicate with one another, forming neural networks.

These neurons take in many inputs, from what we see and hear to how we feel to everything in-between, and then send messages to other neurons, which react in turn. Working neural networks are what enable humans to think, and more importantly, learn.

As a method of taking in large amounts of data, processing it, and making predictions and decisions based on the data, the human brain's neural networks are by far the most powerful computing force known to man.

An illustration of a human bust with the neural pathways of the brain highlighted.
Artificial neural networks are inspired by the complexity of the human neural network.

PASIEKA / Getty Images

Types of Neural Networks

A neural network is technically a biological term, while an artificial neural network is the kind of neural network relied on by artificial intelligence. Though the word itself is most commonly used to refer to the artificial neural network, you will often see people refer to artificial neural networks as simply neural networks.

Naturally, a neural network in the human brain is very different from an artificially constructed neural network. Still, the fundamental way they work to process information and make predictions remains the same.

While an artificial neural network will not be a perfect recreation of a biological neural network, artificial neural networks are based on and modeled after the brain's neural networks, precisely because of the computing power of these networks.

What Are Neural Networks Used For?

Humans use biological neural networks to process information, learn, and make predictions, e.g., think. Artificial neural networks work in much the same way but to a lesser degree, as artificial neural networks cannot yet match the complexity and power of those found in the human brain.

Artificial neural networks enable more complicated, lifelike, and powerful artificial intelligence through deep learning, which is the process of an artificial neural network independently learning and making its own decisions.

Human-like artificial intelligence is possible with an advanced neural network and enough data to train (or teach) the neural network. A.I., as it appears in movies, does not yet exist today, but if it ever does, deep learning through neural networks will power this intelligence.

  • What is a deep neural network?

    Also known as deep learning, it's a sub-field of machine learning in A.I. dealing with algorithms modeled on brain structure and function. Deep neural networks are designed to recognize numerical patterns and translate them into real-world data, such as images, text, or audio.

  • What is a convolutional neural network?

    It's a class of deep neural algorithms often used to analyze visual imagery. A convolutional neural network receives an image and extracts features using filters and is used mainly for image processing, classification, and segmentation.

  • What is a recurrent neural network?

    It's a type of artificial neural network typically used for speech recognition and natural language processing. A recurrent neural network uses sequential data or time-series data to solve common temporal problems in language translation and speech recognition.

Was this page helpful?