Deep learning vs. machine learning: What’s the difference between the two?

deep learning vs machine explained ai 01
In recent months, Microsoft, Google, Apple, Facebook, and other entities have declared that we no longer live in a mobile-first world. Instead, it’s an artificial intelligence-first world where digital assistants and other services will be your primary source of information and getting tasks done. Your typical smartphone or PC are now your secondary go-getters.

Backing this new frontier are two terms you’ll likely hear often: machine learning and deep learning. These are two methods in “teaching” artificial intelligence to perform tasks, but their uses goes way beyond creating smart assistants. What’s the difference? Here’s a quick breakdown.

Computers now see, hear, and speak

With the help of machine learning, computers can now be “trained” to predict the weather, determine stock market outcomes, understand your shopping habits, control robots in a factory, and so on. Google, Amazon, Facebook, Netflix, LinkedIn, and more popular consumer-facing services are all backed by machine learning. But at the heart of all this learning is what’s known as an algorithm.

Simply put, an algorithm is not a complete computer program (a set of instructions), but a limited sequence of steps to solve a single problem. For example, a search engine relies on an algorithm that grabs the text you enter into the search field box, and searches the connected database to provide the related search results. It takes specific steps to achieve a single, specific goal.

Machine learning has actually been around since 1956. Arthur Samuel didn’t want to write a highly-detailed, lengthy program that could enable a computer to beat him in a game of checkers. Instead, he created an algorithm that enabled the computer to play against itself thousands of times so it could “learn” how to perform as a stand-alone opponent. By 1962, this computer beat the Connecticut state champion.

Thus, at its core, machine learning is based on trial and error. We can’t manually write a program by hand that can help a self-driving car distinguish a pedestrian from a tree or a vehicle, but we can create an algorithm for a program that can solve this problem using data. Algorithms can also be created to help programs predict the path of a hurricane, diagnose Alzheimer’s early, determine the world’s most overpaid and underpaid soccer stars, and so on.

Machine learning typically runs on low-end devices, and breaks a problem down into parts. Each part is solved in order, and then combined to create a single answer to the problem. Well-known machine learning contributor Tom Mitchell of Carnegie Mellon University explains that computer programs are “learning” from experience if their performance of a specific task is improving. Machine learning algorithms are essentially enabling programs to make predictions, and over time get better at these predictions based on trial and error experience.

Here are the four main types of machine learning:

Supervised machine learning

In this scenario, you are providing a computer program with labeled data. For instance, if the assigned task is to separate pictures of boys and girls using an algorithm for sorting images, those with a male child would have a “boy” label, and images with a female child would have a “girl” label. This is considered as a “training” dataset, and the labels remain in place until the program can successfully sort the images at an acceptable rate.

Semi-supervised machine learning

In this case, only a few images are labeled. The computer program will then use an algorithm to make its best guess regarding the unlabeled images, and then the data is fed back to the program as training data. A new batch of images is then provided, with only a few sporting labels. It’s a repetitive process until the program can distinguish between boys and girls at an acceptable rate.

Unsupervised machine learning

This type of machine learning doesn’t involve labels whatsoever. Instead, the program is blindly thrown into the task of splitting images of boys and girls into two groups using one of two methods. One algorithm is called “clustering” that groups similar objects together based on characteristics, such as hair length, jaw size, eye placement, and so on. The other algorithm is called “association” where the program creates if/then rules based on similarities it discovers. In other words, it determines a common pattern between the images, and sorts them accordingly.

Reinforcement machine learning

Chess would be an excellent example of this type of algorithm. The program knows the rules of the game and how to play, and goes through the steps to complete the round. The only information provided to the program is whether it won or lost the match. It continues to replay the game, keeping track of its successful moves, until it finally wins a match.

Now it’s time to move on to a deeper subject: deep learning.

Emerging Tech

CES 2019 recap: All the trends, products, and gadgets you missed

CES 2019 didn’t just give us a taste of the future, it offered a five-course meal. From 8K and Micro LED televisions to smart toilets, the show delivered with all the amazing gadgetry you could ask for. Here’s a look at all the big…
Computing

Our favorite Windows apps will help you get the most out of your new PC

Not sure what apps you should be downloading for your newfangled Windows device? Here are the best Windows apps, whether you need something to speed up your machine or access your Netflix queue. Check out our categories and favorite picks.
Emerging Tech

In a first for humankind, China is growing plants on the moon

Having recently landed a probe on the far side of the moon, China announced that it managed to grow the first plant on the moon, too. Here's why that matters for deep space travel.
Smart Home

The best washing machines make laundry day a little less of a chore

It takes a special kind of person to love doing laundry, but the right machine can help make this chore a little easier. Check out our picks for the best washing machines on the market right now.
Smart Home

Military-grade baby monitor called Miku was a hit with parents at CES 2019

Who knew the world needed a smarter baby monitor? Apparently it's the startup Miku, which brought a new high-tech baby monitor to CES 2019 that uses A.I., machine learning, and high quality cameras to keep an eye on kids.
Emerging Tech

Ford’s sweaty robot bottom can simulate 10 years of seat use in mere days

Ford has developed 'Robutt,' a sweaty robot bottom that's designed to simulate the effects of having a pair of human buttocks sitting on its car seats for thousands of hours. Check it out.
Emerging Tech

Want to know which drones are flying near you? There’s an app for that

Want to know what that mysterious drone buzzing over your head is up to? A new system developed by AirMap, Google Wing, and Kittyhawk.io could soon tell you -- via a map on your phone.
Emerging Tech

A Japanese hotel fires half its robot staff for being bad at their jobs

Japan’s oddball Henn na Hotel has fired half of its 243 robot staff. The reason? Because these labor-saving machines turned out to be causing way more problems than they were solving.
Emerging Tech

CERN plans to build a massive particle collider that dwarfs the LHC

CERN already has the world's biggest particle accelerator. Now it wants a bigger one. Meet the 9 billion euro Future Circular Collider that will allow physicists to extend their study of the universe and matter at the smallest level.
Emerging Tech

Forget fireworks. Japan will soon have artificial meteor showers on tap

Tokyo-based startup Astro Live Experiences is preparing to launch its first artificial meteor shower over Japan, serving as a showcase of its prowess in the space entertainment sector.
Cars

Robomart’s self-driving grocery store is like Amazon Go on wheels

Robomart's driverless vehicle is like an Amazon Go store on wheels, with sensors tracking what you grab from the shelves. If you don't want to shop online or visit the grocery store yourself, Robomart will bring the store to you.
Emerging Tech

Glowing space billboards could show ads in the night sky

Look up at the night sky in 2020 and you might see an ad for McDonald's floating among the stars. A Russian startup is working on a project that uses a constellation of small satellites in low-Earth orbit to create glowing ads.
Emerging Tech

New brainwave reader tells teachers if students are concentrating

Massachusetts-based startup BrainCo has developed brainwave-reading headbands which can reportedly help reveal if students are concentrating in class. Here's how they're being used.
Emerging Tech

Fears about kids’ screen use may have been overblown, Oxford researchers find

Many people take it as gospel that digital technologies are harmful to young people’s mental health. But is this true? A recent study from the University of Oxford takes a closer look.
1 of 2