Deep learning vs. machine learning: what's the difference between the two?

You’re starting on page 2 of this, click here to start at the beginning.

Deep Learning

Deep learning is basically machine learning on a “deeper” level (pun unavoidable, sorry). It’s inspired by how the human brain works, but requires high-end machines with discrete add-in graphics cards capable of crunching numbers, and enormous amounts of “big” data. Small amounts of data actually yield lower performance.

Unlike standard machine learning algorithms that break problems down into parts and solves them individually, deep learning solves the problem from end to end. Better yet, the more data and time you feed a deep learning algorithm, the better it gets at solving a task.

In our examples for machine learning, we used images consisting of boys and girls. The program used algorithms to sort these images mostly based on spoon-fed data. But with deep learning, data isn’t provided for the program to use. Instead, it scans all pixels within an image to discover edges that can be used to distinguish between a boy and a girl. After that, it will put edges and shapes into a ranked order of possible importance to determine the two genders.

On an even more simplified level, machine learning will distinguish between a square and triangle based on information provided by humans: squares have four points, and triangles have three. With deep learning, the program doesn’t start out with pre-fed information. Instead, it uses an algorithm to determine how many lines the shapes have, if those lines are connected, and if they are perpendicular. Naturally, the algorithm would eventually figure out that an inserted circle does not fit in with its square and triangle sorting.

Again, this latter “deep thinking” process requires more hardware to process the big data generated by the algorithm. These machines tend to reside in large datacenters to create an artificial neural network to handle all the big data generated and supplied to artificial intelligent applications. Programs using deep learning algorithms also take longer to train because they’re learning on their own instead of relying on hand-fed shortcuts.

“Deep Learning breaks down tasks in ways that makes all kinds of machine assists seem possible, even likely. Driverless cars, better preventive healthcare, even better movie recommendations, are all here today or on the horizon,” writes Nvidia’s Michael Copeland. “With Deep Learning’s help, A.I. may even get to that science fiction state we’ve so long imagined.”

Is Skynet on the way? Not yet

A great recent example of deep learning is translation. This technology is capable of listening to a presenter talking in English, and translating his words into a different language through both text and an electronic voice in real time. This achievement was a slow learning burn over the years due to the differences in overall language, language use, voice pitches, and maturing hardware-based capabilities.

Deep learning is also responsible for conversation-carrying chatbots, Amazon Alexa, Microsoft Cortana, Facebook, Instagram, and more. On social media, algorithms based on deep learning are what cough up contact and page suggestions. Deep learning even helps companies customize their creepy advertising to your tastes even when you’re not on their site. Yay for technology.

“Looking to the future, the next big step will be for the very concept of the ‘device’ to fade away,” says Google CEO Sundar Pichai. “Over time, the computer itself—whatever its form factor—will be an intelligent assistant helping you through your day. We will move from mobile first to an A.I. first world.”

Features

From picking to pollinating, agribots are pushing farming into the future

Farming is becoming increasingly challenging. To deal with environmental pollution, labor shortage, and other major issues, agricultural scientists are turning to robots and AI.
Emerging Tech

Man vs. machine: An A.I. algorithm attempts to break a world speed record

A new machine learning algorithm created at Switzerland’s EPFL is being used to design what its creators hope is the world's fastest bicycle. It will attempt a world record later this year.
Product Review

Do you hear what I hear? Nope. And these headphones adapt for that

A surprising pair of headphones with machine learning and audio probes gets cozy with our inner ears in our Nuraphone Hands-On review.
Computing

The best Windows apps

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!
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.
Photography

What is portrait mode? How tech helps smartphones capture a better you

Several years ago, portrait modes started showing up on phones and quickly became one of the most popular ways to capture selfies, profile pics, and more. But how does portrait mode work, and how much difference does it make?
Emerging Tech

Awesome Tech You Can’t Buy Yet: Laptop screen extenders and self-healing tents

Check out our roundup of the best new crowdfunding projects and product announcements that hit the Web this week. You can't buy this stuff yet, but it sure is fun to gawk!
Smart Home

Put away that sponge and let us help you pick the best dishwasher for your buck

Tired of doing dishes by hand? Take a look at our picks of the four best dishwashers currently available and let a machine do the dirty work for you. They’ll do a much better job, anyway.
Cars

Shift it yourself: How to drive stick in a manual transmission car

It might seem intimidating, but anyone can drive a manual transmission car. Knowing how to operate this type of gearbox will serve you well. Here's everything you need to know to learn how to drive stick.
Movies & TV

The '80s are alive as first 'Stranger Things' season 3 teaser goes to the mall

With a sophomore season as strong as its first, Stranger Things is now moving on to season 3. Here's everything we've learned so far about the Netflix series' upcoming third season.
Home Theater

The ultimate surround sound guide: Different formats explained

Wondering which is the best surround sound format for your home theater system? Start by learning the technical differences between the various formats with our ultimate surround sound guide.
Mobile

How to improve your Android privacy

If you have an Android device and you’re concerned about your privacy, then we have a few tips for you. Learn about the settings you can change to improve your Android privacy and safeguard your personal data.
Smart Home

Every parent’s nightmare: A 3-year-old gets trapped in a washing machine

When kids begin expressing interest in helping around the house -- poking around the dishwasher or learning about the laundry -- parents normally rejoice. But that was not the case for one 3-year-old trapped in a washer.
Photography

6 pro tips for taking amazing portrait photos with the Huawei P10

To really show us what the P10's Leica camera and its Portrait mode can do, a pro-photographer taught us how to use it. We learned plenty. Here are the best tips for perfect portraits and selfies.
Computing

Gaming on a laptop has never been better. These are your best options

Gaming desktops are powerful, but they tie you down to your desk. For those of us who prefer a more mobile experience, here are the best gaming laptops on the market, ranging from budget machines to maxed-out, wallet-emptying PCs.
Emerging Tech

Blue Origin reaches a big milestone, lands rocket booster and crew capsule

Jeff Bezos' space endeavor Blue Origin recently completed its most important test -- a live separation of its crew capsule from its rocket booster. More than 20,000 people tuned into the livestream.
Emerging Tech

Bright idea: Keep your gadgets juiced up with these stellar solar chargers

Looking for a gizmo that can help you charge your phone while on the go? Here, we've outlined the best solar chargers on the market, whether you're looking to charge your phone once, twice, or three times over.
Emerging Tech

Geologists discover a quadrillion tons of diamonds that are impossible to reach

Researchers have discovered that there may very well be a quadrillion tons of diamonds buried 100 miles below Earth's surface. The bad part? Sadly, they're impossible to reach right now.
Emerging Tech

Genetically modified bacteria may be the key to plants that fertilize themselves

Scientists from Washington University in St. Louis have developed genetically engineered bacteria capable of pulling fertilizer out of thin air. Here's why that's such a potential game-changer.
Emerging Tech

Gotta catch em all: Harvard’s undersea grabber is a Poké Ball for sea life

Harvard’s new folding origami robot grabber is designed to perform delicate feats, such as catching underwater creatures with ease -- and crucially, without injuring them in the process.
Emerging Tech

Moving around in zero gravity is hard. MIT’s solution? Spider-Man’s web shooter

Researchers from MIT have been researching ways for astronauts to easily move around in microgravity. One solution is that they can use Spider-Man-style web shooters to pull themselves around.
Emerging Tech

World’s first VR-augmented waterslide is totally unnecessary, but also amazing

An amusement park in Germany unveiled the world's first waterslide that requires riders to wear a virtual reality headset. Here's what went into making this waterlogged VR dream a reality.
Emerging Tech

Rolls-Royce is creating a fleet of robotic snakes and beetles to repair planes

Researchers from Rolls-Royce are creating snake and insect-swarm-inspired robots that are designed to crawl inside airplane engines to carry out inspections and perform maintenance.
2 of 2