This is the first of a multi-part series explaining the fundamentals of deep learning by long-time tech journalist Michael Copeland. Bạn đang xem: Deep learning và machine learning
Bạn đang xem: Deep learning và machine learning
Artificial intelligence is the future. Artificial intelligence is science fiction. Artificial intelligence is already part of our everyday lives. All those statements are true, it just depends on what flavor of AI you are referring to.
For example, when Google DeepMind’s AlphaGo program defeated South Korean Master Lee Se-dol in the board trò chơi Go earlier this year, the terms AI, machine learning, và deep learning were used in the media to describe how DeepMind won. And all three are part of the reason why AlphaGo trounced Lee Se-Dol. But they are not the same things.
The easiest way lớn think of their relationship is lớn visualize them as concentric circles with AI — the idea that came first — the largest, then machine learning — which blossomed later, & finally deep learning — which is driving today’s AI explosion — fitting inside both.
From Bust lớn BoomAI has been part of our imaginations and simmering in research labs since a handful of computer scientists rallied around the term at the Dartmouth Conferences in 1956 and birthed the field of AI. In the decades since, AI has alternately been heralded as the key lớn our civilization’s brightest future, và tossed on technology’s trash heap as a harebrained notion of over-reaching propellerheads. Frankly, until 2012, it was a bit of both.
Over the past few years AI has exploded, & especially since 2015. Much of that has to vì chưng with the wide availability of GPUs that make parallel processing ever faster, cheaper, và more powerful. It also has to vì chưng with the simultaneous one-two punch of practically infinite storage và a flood of data of every stripe (that whole Big Data movement) – images, text, transactions, mapping data, you name it.
Let’s walk through how computer scientists have moved from something of a bust — until 2012 — lớn a boom that has unleashed applications used by hundreds of millions of people every day.
Artificial Intelligence — Human Intelligence Exhibited by Machines
What we can bởi vì falls into the concept of “Narrow AI.” Technologies that are able khổng lồ perform specific tasks as well as, or better than, we humans can. Examples of narrow AI are things such as image classification on a service lượt thích Pinterest and face recognition on Facebook.
Those are examples of Narrow AI in practice. These technologies exhibit some facets of human intelligence. But how? Where does that intelligence come from? That get us khổng lồ the next circle, machine learning.
Machine Learning — An Approach to Achieve Artificial Intelligence
Machine learning came directly from minds of the early AI crowd, and the algorithmic approaches over the years included decision tree learning, inductive súc tích programming. Clustering, reinforcement learning, and Bayesian networks among others. As we know, none achieved the ultimate goal of General AI, & even Narrow AI was mostly out of reach with early machine learning approaches.
To learn more about deep learning, listen to lớn the 113th episode of our AI Podcast with thanhtuong.vn’s Will Ramey
As it turned out, one of the very best application areas for machine learning for many years was computer vision, though it still required a great khuyến mãi of hand-coding khổng lồ get the job done. People would go in and write hand-coded classifiers lượt thích edge detection filters so the program could identify where an object started và stopped; shape detection lớn determine if it had eight sides; a classifier khổng lồ recognize the letters “S-T-O-P.” From all those hand-coded classifiers they would develop algorithms to lớn make sense of the image and “learn” to lớn determine whether it was a stop sign.
Good, but not mind-bendingly great. Especially on a foggy day when the sign isn’t perfectly visible, or a tree obscures part of it. There’s a reason computer vision and image detection didn’t come close lớn rivaling humans until very recently, it was too brittle & too prone lớn error.
Time, và the right learning algorithms made all the difference.
Deep Learning — A Technique for Implementing Machine Learning
You might, for example, take an image, chop it up into a bunch of tiles that are inputted into the first layer of the neural network. In the first layer individual neurons, then passes the data khổng lồ a second layer. The second layer of neurons does its task, and so on, until the final layer & the final output đầu ra is produced.
Each neuron assigns a weighting to lớn its đầu vào — how correct or incorrect it is relative to the task being performed. The final output đầu ra is then determined by the total of those weightings. So think of our stop sign example. Attributes of a stop sign image are chopped up & “examined” by the neurons — its octogonal shape, its fire-engine red color, its distinctive letters, its traffic-sign size, and its motion or lack thereof. The neural network’s task is lớn conclude whether this is a stop sign or not. It comes up with a “probability vector,” really a highly educated guess, based on the weighting. In our example the system might be 86% confident the image is a stop sign, 7% confident it’s a tốc độ limit sign, và 5% it’s a kite stuck in a tree ,and so on — & the network architecture then tells the neural network whether it is right or not.
Even this example is getting ahead of itself, because until recently neural networks were all but shunned by the AI research community. They had been around since the earliest days of AI, và had produced very little in the way of “intelligence.” The problem was even the most basic neural networks were very computationally intensive, it just wasn’t a practical approach. Still, a small heretical research group led by Geoffrey Hinton at the University of Toronto kept at it, finally parallelizing the algorithms for supercomputers to lớn run và proving the concept, but it wasn’t until GPUs were deployed in the effort that the promise was realized.
If we go back again to lớn our stop sign example, chances are very good that as the network is getting tuned or “trained” it’s coming up with wrong answers — a lot. What it needs is training. It needs khổng lồ see hundreds of thousands, even millions of images, until the weightings of the neuron inputs are tuned so precisely that it gets the answer right practically every time — fog or no fog, sun or rain. It’s at that point that the neural network has taught itself what a stop sign looks like; or your mother’s face in the case of Facebook; or a cat, which is what Andrew Ng did in 2012 at Google.
Ng’s breakthrough was lớn take these neural networks, and essentially make them huge, increase the layers và the neurons, and then run massive amounts of data through the system to train it. In Ng’s case it was images from 10 million YouTube videos. Ng put the “deep” in deep learning, which describes all the layers in these neural networks.
Today, image recognition by machines trained via deep learning in some scenarios is better than humans, & that ranges from cats khổng lồ identifying indicators for cancer in blood and tumors in MRI scans. Google’s AlphaGo learned the game, & trained for its Go match — it tuned its neural network — by playing against itself over and over & over.
Thanks lớn Deep Learning, AI Has a Bright Future
Deep learning has enabled many practical applications of machine learning and by extension the overall field of AI. 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. AI is the present và the future. With Deep learning’s help, AI may even get khổng lồ that science fiction state we’ve so long imagined. You have a C-3PO, I’ll take it. You can keep your Terminator.