What is an artificial neural network? Here’s everything you need to know

artificial neural network
Michael Tyka

If you’ve spent any time reading about artificial intelligence, you’ll almost certainly have heard about artificial neural networks. But what exactly is one? Rather than enrolling in a comprehensive computer science course or delving into some of the more in-depth resources that are available online, check out our handy layperson’s guide to get a quick and easy introduction to this amazing form of machine learning.

What is an artificial neural network?

Artificial neural networks are one of the main tools used in machine learning. As the “neural” part of their name suggests, they are brain-inspired systems which are intended to replicate the way that we humans learn. Neural networks consist of input and output layers, as well as (in most cases) a hidden layer consisting of units that transform the input into something that the output layer can use. They are excellent tools for finding patterns which are far too complex or numerous for a human programmer to extract and teach the machine to recognize.

While neural networks (also called “perceptrons”) have been around since the 1940s, it is only in the last several decades where they have become a major part of artificial intelligence. This is due to the arrival of a technique called “backpropagation,” which allows networks to adjust their hidden layers of neurons in situations where the outcome doesn’t match what the creator is hoping for — like a network designed to recognize dogs, which misidentifies a cat, for example.

Another important advance has been the arrival of deep learning neural networks, in which different layers of a multilayer network extract different features until it can recognize what it is looking for.

Sounds pretty complex. Can you explain it like I’m five?

For a basic idea of how a deep learning neural network learns, imagine a factory line. After the raw materials (the data set) are input, they are then passed down the conveyer belt, with each subsequent stop or layer extracting a different set of high-level features. If the network is intended to recognize an object, the first layer might analyze the brightness of its pixels.

what is an artificial neural network 1

The next layer could then identify any edges in the image, based on lines of similar pixels. After this, another layer may recognize textures and shapes, and so on. By the time the fourth or fifth layer is reached, the deep learning net will have created complex feature detectors. It can figure out that certain image elements (such as a pair of eyes, a nose, and a mouth) are commonly found together.

Once this is done, the researchers who have trained the network can give labels to the output, and then use backpropagation to correct any mistakes which have been made. After a while, the network can carry out its own classification tasks without needing humans to help every time.

Beyond this, there are different types of learning, such as supervised or unsupervised learning or reinforcement learning, in which the network learns for itself by trying to maximize its score — as memorably carried out by Google DeepMind’s Atari game-playing bot.

How many types of neural network are there?

There are multiple types of neural network, each of which come with their own specific use cases and levels of complexity. The most basic type of neural net is something called a feedforward neural network, in which information travels in only one direction from input to output.

A more widely used type of network is the recurrent neural network, in which data can flow in multiple directions. These neural networks possess greater learning abilities and are widely employed for more complex tasks such as learning handwriting or language recognition.

There are also convolutional neural networks, Boltzmann machine networks, Hopfield networks, and a variety of others. Picking the right network for your task depends on the data you have to train it with, and the specific application you have in mind. In some cases, it may be desirable to use multiple approaches, such as would be the case with a challenging task like voice recognition.

What kind of tasks can a neural network do?

A quick scan of our archives suggests the proper question here should be “what tasks can’t a neural network do?” From making cars drive autonomously on the roads, to generating shockingly realistic CGI faces, to machine translation, to fraud detection, to reading our minds, to recognizing when a cat is in the garden and turning on the sprinklers; neural nets are behind many of the biggest advances in A.I.

faception facial recognition

Broadly speaking, however, they are designed for spotting patterns in data. Specific tasks could include classification (classifying data sets into predefined classes), clustering (classifying data into different undefined categories), and prediction (using past events to guess future ones, like the stock market or movie box office).

How exactly do they “learn” stuff?

In the same way that we learn from experience in our lives, neural networks require data to learn. In most cases, the more data that can be thrown at a neural network, the more accurate it will become. Think of it like any task you do over and over. Over time, you gradually get more efficient and make fewer mistakes.

When researchers or computer scientists set out to train a neural network, they typically divide their data into three sets. First is a training set, which helps the network establish the various weights between its nodes. After this, they fine-tune it using a validation data set. Finally, they’ll use a test set to see if it can successfully turn the input into the desired output.

Do neural networks have any limitations?

On a technical level, one of the bigger challenges is the amount of time it takes to train networks, which can require a considerable amount of compute power for more complex tasks. The biggest issue, however, is that neural networks are “black boxes,” in which the user feeds in data and receives answers. They can fine-tune the answers, but they don’t have access to the exact decision making process.

This is a problem a number of researchers are actively working on, but it will only become more pressing as artificial neural networks play a bigger and bigger role in our lives.

News

Random people might have listened to your Google Assistant commands

The Belgian public broadcasting network VRT NWS issued a report that confirms Google uses professional contractors to transcribe commands given to their smart assistants -- and in doing so reveals personal information.
Deals

The Google Pixel 3 XL is $250 off for Prime Day

The Google Pixel 3 XL is one of the best phones of the last year, thanks to the fact that it has an amazing camera and super smart artificial intelligence features. For Amazon Prime Day 2019, the device has been discounted by around a hefty…
Mobile

Sprint's growing 5G network is now available in Chicago

Sprint has launched its next-gen 5G network in a handful of cities, but more are on the way soon. But the 5G network it's using is a decidedly different approach than some of its competitors, including Verizon and AT&T.
Cars

Jaguar Land Rover built an A.I.-equipped car that responds to the driver’s mood

Jaguar Land Rover is testing a system that uses a driver-facing camera and artificial intelligence to read a person's mood. The automaker believes this tech could be used to reduce stress while driving.
Emerging Tech

Meet NASA’s climbing robots, able to move through the slipperiest environments

When it comes to exploring far off planets, robots need to be able to tackle all sorts of environmental challenges. NASA has been working on a series of climbing robots to take on different tasks in inhospitable environments.
Emerging Tech

Bouncing robot for low-gravity space missions has a spring in its step

The European Space Agency has created SpaceBok, a robot inspired by the springbok designed for low-gravity dynamic walking. On the moon, SpaceBok could potentially jump as high as two meters into the air.
Emerging Tech

Impossible Foods looks to make another splash with fishless fish

Impossible Foods is currently developing fishless fish, in response to the growing demand for plant-based food. The product will include heme, a protein from genetically modified yeast that was also used in the Impossible Burger.
Cars

Awesome Tech You Can’t Buy Yet: Drone lens, laser synth, and more

Check out our roundup of the best new crowdfunding projects and product announcements that hit the web this week. You may not be able to buy this stuff yet, but it sure is fun to gawk!
Emerging Tech

Professional poker players no match for A.I. in six-player Texas Hold ’em

Poker AI Pluribus destroyed professional players in Texas Hold 'em. The bot won an average of $5 per hand with winnings of $1,000 per hour, with strategies that were very different to how humans played the game.
Emerging Tech

Russia launches X-ray observatory capable of locating thousands of black holes

Russia has finally launched its powerful X-ray observatory, Spektr-RG, after a delay caused by faulty batteries on board the spacecraft. The launch took place at 5:30 a.m. PT on Saturday, July 13, taking off from the Baikonur Cosmodrome.
Emerging Tech

See a gargantuan dust storm covering the north pole of Mars

A dust storm around Mars' north pole has been imaged by the Mars Express orbiter. Localized dust storms are common on Mars, but occasionally one expands into a planet-wide event like the one which caused the demise of the Opportunity rover.
Emerging Tech

The Very Large Telescope captures the beautiful remnants of a dying star

The VLT has captured a beautiful cosmic object, the planetary nebula named Abell 24. Located in constellation of Canis Minor (The Lesser Dog), it is a swirl of dust and gas which is illuminated by the core of a dead star.
Emerging Tech

Astronomers have spotted a moon forming around a proto-Jupiter

Astronomers have spotted a young planet with a disk of gas and dust around it which is similar to the one from which the moons of Jupiter were born. The planet PDS 70 b is in the process of forming and is located 370 light-years away.
Emerging Tech

Stallone in Terminator 2? How one deepfake prankster is changing cinema history

Ever wanted to see The Shining with Jim Carrey instead of Jack Nicholson? How about Stallone in Terminator 2: Judgement Day instead of everyone's favorite governator? Thanks to deepfakes, it's now possible -- just ask YouTuber Ctrl Shift…