What is deep learning?

Curious how A.I. 'brains' work? Here's a super-simple breakdown of deep learning

Deep learning is a particular subset of machine learning (the mechanics of artificial intelligence). While this branch of programming can become very complex, it started with a very simple question: “If we want a computer system to act intelligently, why don’t we model it after the human brain?”

That one thought spawned many efforts in past decades to create algorithms that mimicked the way the human brain worked—and that could solve problems the way that humans did. Those efforts have yielded valuable, increasingly competent analysis tools that are used in many different fields.

The neural network and how it’s used

Neural Network Chart
via Wikipedia

Deep learning gets its name from how it’s used to analyze “unstructured” data, or data that hasn’t been previously labeled by another source and may need definition. That requires careful analysis of what the data is, and repeated tests of that data to end up with a final, usable conclusion. Computers are not traditionally good at analyzing unstructured data like this.

Think about it in terms of writing: If you had ten people write the same word, that word would look very different from each person, from sloppy to neat, and from cursive to print. The human brain has no problem understanding that it’s all the same word, because it knows how words, writing, paper, ink, and personal quirks all work. A normal computer system, however, would have no way of knowing that those words are the same, because they all look so different.

That brings us to via neural networks, the algorithms specifically created to mimic the way that the neurons in the brain interact. Neural networks attempt to parse data the way that a mind can: Their goal is to deal with messy data—like writing—and draw useful conclusions, like the words that writing is attempting to show. It’s easiest to understand neural networks if we break them into three important parts:

The input layer: At the input layer, the neural network absorbs all the unclassified data that it is given. This means breaking down the information into numbers and turning them into bits of yes-or-no data, or “neurons”. If you wanted to teach a neural network to recognize words, then the input layer would be mathematically defining the shape of each letter, breaking it down into digital language so the network can start working. The input layer can be pretty simple or incredibly complex, depending on how easy it is to represent something mathematically.

Complex Neural Network
via Wikimedia

The hidden layers: At the center of the neural network are hidden layers—anywhere from one to many. These layers are made of their own digital neurons, which are designed to activate or not activate based on the layer of neurons that precedes them. A single neuron is a basic “if this, then that model, but layers are made of long chains of neurons, and many different layers can influence each other, creating very complex results. The goal is to allow the neural network to recognize many different features and combine them into a single realization, like a child learning to recognize each letter and then forming them together to recognize a full word, even if that word is written a little sloppy.

The hidden layers are also where a lot of deep learning training goes on. For example, if the algorithm failed to accurately recognize a word, programmers send back, “Sorry, that’s not correct,” and the algorithm would adjust how it weighed data until it found the right answers. Repeating this process (programmers may also adjust weights manually) allows the neural network to build up robust hidden layers that are adept at seeking out the right answers through a lot of trial and error plus, some outside instruction — again, much like how the human brain works. As the above image shows, hidden layers can become very complex!

The output layer: The output layer has relatively few “neurons” because it’s where the final decisions are made. Here the neural network applies the final analysis, settles on definitions for the data, and draws the programmed conclusions based on those definitions. For example, “Enough of the data lines up to say that this word is lake, not lane.” Ultimately all data that passes through the network is narrowed down to specific neurons in the output layer. Since this is where the goals are realized, it’s often one of the first parts of the network created.


Eye Scan Army

If you use modern technology, chances are good that deep learning algorithms are at work all around you, every day. How do you think Alexa or Google Assistant understand your voice commands? They use neural networks that have been built to understand speech. How does Google know what you’re searching for before you’re done typing? More deep learning at work. How does your security cam ignore pets but recognize human movement? Deeping learning once again.

Anytime that software recognizes human inputs, from facial recognition to voice assistants, deep learning is probably at work somewhere underneath. However, the field also has many other useful applications. Medicine is a particularly promising field, where advanced deep learning is used to analyze DNA for flaws or molecular compounds for potential health benefits. On a more physical front, deep learning is used in a growing number of machines and vehicles to predict when equipment needs maintenance before something goes seriously wrong.

The future of deep learning

History of AI name

The future of deep learning is particularly bright! The great thing about a neural network is that it excels at dealing with a vast amount of disparate data (think of everything our brains have to deal with, all the time). That’s especially relevant in our era of advanced smart sensors, which can gather an incredible amount of information. Traditional computer solutions are beginning to struggle with sorting, labeling and drawing conclusions from so much data.

Deep learning, on the other hand, can deal with the digital mountains of data we are gathering. In fact, the larger the amount of data, the more efficient deep learning becomes compared to other methods of analysis. This is why organizations like Google invest so much in deep learning algorithms, and why they are likely to become more common in the future.

And, of course, the robots. Let’s never forget about the robots.

Emerging Tech

A.I.-generated text is supercharging fake news. This is how we fight back

A new A.I. tool is reportedly able to spot passages of text written by algorithm. Here's why similar systems might prove essential in a world of fake news created by smart machines.
Emerging Tech

Researchers gave alligators headphones and ketamine, and all for a good cause

Researchers in Germany and the United States recently gave ketamine and earphones to alligators to monitor how they process sounds. Here's what it reveals about alligator evolution.

Nvidia’s smart paintbrush tool turns simple doodles into works of art

Nvidia has announced a new deep-learning-enhanced drawing app that can turn your doodles and sketches into highly realistic images. With Nvidia's GauGAN, simple sketches can be automatically embellished with more vivid details.
Movies & TV

Did I really watch that? Here's how to delete your Netflix viewing history

Everybody has some skeletons in their streaming closet, but you don't have to live with them if you don't want to. Learning how to delete your Netflix viewing history is easy, and we're here to help.
Emerging Tech

Take a dip in the Lagoon Nebula in first image from SPECULOOS instrument

The European Southern Observatory has released the first image collected by their new SPECULOOS instrument, and it's a stunning portrait of the Lagoon Nebula, a swirling cloud of dust and gas where new stars are born.
Emerging Tech

Robot assistants from Toyota and Panasonic gear up for the Tokyo Olympics

Japan plans to use the 2020 Olympics to showcase a range of its advanced technologies. Toyota and Panasonic are already getting in on the act, recently unveiling several robotic designs that they intend to deploy at the event.
Emerging Tech

Racing to catch a flight? Robot valet at French airport will park your car

Hate searching for parking at the airport when you need to catch a plane? Startup Stanley Robotics recently unveiled a new outdoor automated robotic valet system. Here's how it works.

Bags with brains: Smart luggage and gadgets are making travel smoother

The bag you use to tote your stuff can affect the experience of any trip. In response, suitcases are wising up, and there are now options for smart luggage with scales, tracking, and more. Here are our favorite pieces.

At $99, Nvidia’s Jetson Nano minicomputer seeks to bring robotics to the masses

Nvidia announced a new A.I. computer, the Jetson Nano. This computer comes with an 128-core GPU that Nvidia claims can handle pretty much any A.I. framework you could imagine. At $99, it's an affordable way for A.I. newbies to get involved.

Nvidia’s A.I. Playground lets you edit photos, experience deep learning research

Nvidia is making it easier to access information on deep learning research. It has launched an online space with three demos for image editing, styling, as well as photorealistic image synthesis. 

British Airways’ new Club Suite for business class comes with a door

British Airways is going after a bigger slice of the business class market with the imminent launch of the Club Suite. The plush seating option offers a more private space as well as an easier route to the bathroom.
Smart Home

Sony’s Aibo robot dog can now patrol your home for persons of interest

Sony released the all-new Aibo in the U.S. around nine months ago, and since then the robot dog has (hopefully) been melting owners' hearts with its cute looks and clever tricks. Now it has a new one up its sleeve.
Emerging Tech

Inflating smart pills could be a painless alternative to injections

Could an inflating pill containing hidden microneedles replace painful injections? The creators of the RaniPill robotic capsule think so — and they have the human trials to prove it.
Emerging Tech

The U.S. Army is building a giant VR battlefield to train soldiers virtually

Imagine if the U.S. Army was able to rehearse battlezone scenarios dozens, or even hundreds, or times before settling foot on actual terrain. Thanks to virtual reality, that's now a possibility.