Understanding the limits of deep learning Posted on : Apr 05 - 2017

Artificial intelligence has reached peak hype. News outlets report that companies have replaced workers with IBM Watson and that algorithms are beating doctors at diagnoses. New AI startups pop up everyday, claiming to solve all your personal and business problems with machine learning.

Ordinary objects like juicers and Wi-Fi routers suddenly advertise themselves as “powered by AI.” Not only can smart standing desks remember your height settings, they can also order you lunch.

Much of the AI hubbub is generated by reporters who’ve never trained a neural network and by startups or those hoping to be acqui-hired for engineering talent despite not having solved any real business problems. No wonder there are so many misconceptions about what AI can and cannot do.

Deep learning is undeniably mind-blowing

Neural networks were invented in the ’60s, but recent boosts in big data and computational power made them actually useful. A new discipline called “deep learning” has arisen that can apply complex neural network architectures to model patterns in data more accurately than ever before.

The results are undeniably impressive. Computers can now recognize objects in images and video and transcribe speech to text better than humans can. Google replaced Google Translate’s architecture with neural networks, and now machine translation is also closing in on human performance.

The practical applications are mind-blowing as well. Computers can predict crop yield better than the USDA and indeed diagnose cancer more accurately than elite physicians.

John Launchbury, a director at DARPA, describes three waves of artificial intelligence:

1. Handcrafted knowledge, or expert systems like IBM’s Deep Blue or Watson

2. Statistical learning, which includes machine learning and deep learning

3. Contextual adaption, which involves constructing reliable, explanatory models for real-world phenomena using sparse data, like humans do

As part of the current second wave of AI, deep learning algorithms work well because of what Launchbury calls the “manifold hypothesis” (see below). In simplified terms, this refers to how different types of high-dimensional natural data tend to clump and be shaped differently when visualized in lower dimensions.

By mathematically manipulating and separating data clumps, deep neural networks can distinguish different data types. While neural nets can achieve nuanced classification and predication capabilities, they are essentially what Launchbury calls “spreadsheets on steroids.”

Deep learning also has deep problems

At the recent AI By The Bay conference, Francois Chollet emphasized that deep learning is simply more powerful pattern recognition than previous statistical and machine learning methods. “The most important problem for AI today is abstraction and reasoning,” explains Chollet, an AI researcher at Google and famed inventor of widely used deep learning library Keras. “Current supervised perception and reinforcement learning algorithms require lots of data, are terrible at planning, and are only doing straightforward pattern recognition.”

By contrast, humans “learn from very few examples, can do very long-term planning, and are capable of forming abstract models of a situation and [manipulating] these models to achieve extreme generalization.”

Even simple human behaviors are laborious to teach to a deep learning algorithm. Let’s examine a situation such as avoiding being hit by a car as you walk down the road. If you go the supervised learning route, you’d need huge data sets of car situations with clearly labeled actions to take, such as “stop” or “move.” Then you’d need to train a neural network to learn the mapping between the situation and the appropriate action.

If you go the reinforcement learning route, where you give an algorithm a goal and let it independently determine the ideal actions to take, the computer would need to die thousands of times before learning to avoid cars in different situations.

“You cannot achieve general intelligence simply by scaling up today’s deep learning techniques,” warns Chollet.

Humans only need to be told once to avoid cars. We’re equipped with the ability to generalize from just a few examples and are capable of imagining (i.e. modeling) the dire consequences of being run over. Without losing life or limb, most of us quickly learn to avoid being overrun by motor vehicles.

While neural networks achieve statistically impressive results across large sample sizes, they are “individually unreliable” and often make mistakes humans would never make, such as classifying a toothbrush as a baseball bat. View More