Tag Archives: show
#432181 Putting AI in Your Pocket: MIT Chip Cuts ...
Neural networks are powerful things, but they need a lot of juice. Engineers at MIT have now developed a new chip that cuts neural nets’ power consumption by up to 95 percent, potentially allowing them to run on battery-powered mobile devices.
Smartphones these days are getting truly smart, with ever more AI-powered services like digital assistants and real-time translation. But typically the neural nets crunching the data for these services are in the cloud, with data from smartphones ferried back and forth.
That’s not ideal, as it requires a lot of communication bandwidth and means potentially sensitive data is being transmitted and stored on servers outside the user’s control. But the huge amounts of energy needed to power the GPUs neural networks run on make it impractical to implement them in devices that run on limited battery power.
Engineers at MIT have now designed a chip that cuts that power consumption by up to 95 percent by dramatically reducing the need to shuttle data back and forth between a chip’s memory and processors.
Neural nets consist of thousands of interconnected artificial neurons arranged in layers. Each neuron receives input from multiple neurons in the layer below it, and if the combined input passes a certain threshold it then transmits an output to multiple neurons above it. The strength of the connection between neurons is governed by a weight, which is set during training.
This means that for every neuron, the chip has to retrieve the input data for a particular connection and the connection weight from memory, multiply them, store the result, and then repeat the process for every input. That requires a lot of data to be moved around, expending a lot of energy.
The new MIT chip does away with that, instead computing all the inputs in parallel within the memory using analog circuits. That significantly reduces the amount of data that needs to be shoved around and results in major energy savings.
The approach requires the weights of the connections to be binary rather than a range of values, but previous theoretical work had suggested this wouldn’t dramatically impact accuracy, and the researchers found the chip’s results were generally within two to three percent of the conventional non-binary neural net running on a standard computer.
This isn’t the first time researchers have created chips that carry out processing in memory to reduce the power consumption of neural nets, but it’s the first time the approach has been used to run powerful convolutional neural networks popular for image-based AI applications.
“The results show impressive specifications for the energy-efficient implementation of convolution operations with memory arrays,” Dario Gil, vice president of artificial intelligence at IBM, said in a statement.
“It certainly will open the possibility to employ more complex convolutional neural networks for image and video classifications in IoT [the internet of things] in the future.”
It’s not just research groups working on this, though. The desire to get AI smarts into devices like smartphones, household appliances, and all kinds of IoT devices is driving the who’s who of Silicon Valley to pile into low-power AI chips.
Apple has already integrated its Neural Engine into the iPhone X to power things like its facial recognition technology, and Amazon is rumored to be developing its own custom AI chips for the next generation of its Echo digital assistant.
The big chip companies are also increasingly pivoting towards supporting advanced capabilities like machine learning, which has forced them to make their devices ever more energy-efficient. Earlier this year ARM unveiled two new chips: the Arm Machine Learning processor, aimed at general AI tasks from translation to facial recognition, and the Arm Object Detection processor for detecting things like faces in images.
Qualcomm’s latest mobile chip, the Snapdragon 845, features a GPU and is heavily focused on AI. The company has also released the Snapdragon 820E, which is aimed at drones, robots, and industrial devices.
Going a step further, IBM and Intel are developing neuromorphic chips whose architectures are inspired by the human brain and its incredible energy efficiency. That could theoretically allow IBM’s TrueNorth and Intel’s Loihi to run powerful machine learning on a fraction of the power of conventional chips, though they are both still highly experimental at this stage.
Getting these chips to run neural nets as powerful as those found in cloud services without burning through batteries too quickly will be a big challenge. But at the current pace of innovation, it doesn’t look like it will be too long before you’ll be packing some serious AI power in your pocket.
Image Credit: Blue Planet Studio / Shutterstock.com Continue reading
#432031 Why the Rise of Self-Driving Vehicles ...
It’s been a long time coming. For years Waymo (formerly known as Google Chauffeur) has been diligently developing, driving, testing and refining its fleets of various models of self-driving cars. Now Waymo is going big. The company recently placed an order for several thousand new Chrysler Pacifica minivans and next year plans to launch driverless taxis in a number of US cities.
This deal raises one of the biggest unanswered questions about autonomous vehicles: if fleets of driverless taxis make it cheap and easy for regular people to get around, what’s going to happen to car ownership?
One popular line of thought goes as follows: as autonomous ride-hailing services become ubiquitous, people will no longer need to buy their own cars. This notion has a certain logical appeal. It makes sense to assume that as driverless taxis become widely available, most of us will eagerly sell the family car and use on-demand taxis to get to work, run errands, or pick up the kids. After all, vehicle ownership is pricey and most cars spend the vast majority of their lives parked.
Even experts believe commercial availability of autonomous vehicles will cause car sales to drop.
Market research firm KPMG estimates that by 2030, midsize car sales in the US will decline from today’s 5.4 million units sold each year to nearly half that number, a measly 2.1 million units. Another market research firm, ReThinkX, offers an even more pessimistic estimate (or optimistic, depending on your opinion of cars), predicting that autonomous vehicles will reduce consumer demand for new vehicles by a whopping 70 percent.
The reality is that the impending death of private vehicle sales is greatly exaggerated. Despite the fact that autonomous taxis will be a beneficial and widely-embraced form of urban transportation, we will witness the opposite. Most people will still prefer to own their own autonomous vehicle. In fact, the total number of units of autonomous vehicles sold each year is going to increase rather than decrease.
When people predict the demise of car ownership, they are overlooking the reality that the new autonomous automotive industry is not going to be just a re-hash of today’s car industry with driverless vehicles. Instead, the automotive industry of the future will be selling what could be considered an entirely new product: a wide variety of intelligent, self-guiding transportation robots. When cars become a widely used type of transportation robot, they will be cheap, ubiquitous, and versatile.
Several unique characteristics of autonomous vehicles will ensure that people will continue to buy their own cars.
1. Cost: Thanks to simpler electric engines and lighter auto bodies, autonomous vehicles will be cheaper to buy and maintain than today’s human-driven vehicles. Some estimates bring the price to $10K per vehicle, a stark contrast with today’s average of $30K per vehicle.
2. Personal belongings: Consumers will be able to do much more in their driverless vehicles, including work, play, and rest. This means they will want to keep more personal items in their cars.
3. Frequent upgrades: The average (human-driven) car today is owned for 10 years. As driverless cars become software-driven devices, their price/performance ratio will track to Moore’s law. Their rapid improvement will increase the appeal and frequency of new vehicle purchases.
4. Instant accessibility: In a dense urban setting, a driverless taxi is able to show up within minutes of being summoned. But not so in rural areas, where people live miles apart. For many, delay and “loss of control” over their own mobility will increase the appeal of owning their own vehicle.
5. Diversity of form and function: Autonomous vehicles will be available in a wide variety of sizes and shapes. Consumers will drive demand for custom-made, purpose-built autonomous vehicles whose form is adapted for a particular function.
Let’s explore each of these characteristics in more detail.
Autonomous vehicles will cost less for several reasons. For one, they will be powered by electric engines, which are cheaper to construct and maintain than gasoline-powered engines. Removing human drivers will also save consumers money. Autonomous vehicles will be much less likely to have accidents, hence they can be built out of lightweight, lower-cost materials and will be cheaper to insure. With the human interface no longer needed, autonomous vehicles won’t be burdened by the manufacturing costs of a complex dashboard, steering wheel, and foot pedals.
While hop-on, hop-off autonomous taxi-based mobility services may be ideal for some of the urban population, several sizeable customer segments will still want to own their own cars.
These include people who live in sparsely-populated rural areas who can’t afford to wait extended periods of time for a taxi to appear. Families with children will prefer to own their own driverless cars to house their childrens’ car seats and favorite toys and sippy cups. Another loyal car-buying segment will be die-hard gadget-hounds who will eagerly buy a sexy upgraded model every year or so, unable to resist the siren song of AI that is three times as safe, or a ride that is twice as smooth.
Finally, consider the allure of robotic diversity.
Commuters will invest in a home office on wheels, a sleek, traveling workspace resembling the first-class suite on an airplane. On the high end of the market, city-dwellers and country-dwellers alike will special-order custom-made autonomous vehicles whose shape and on-board gadgetry is adapted for a particular function or hobby. Privately-owned small businesses will buy their own autonomous delivery robot that could range in size from a knee-high, last-mile delivery pod, to a giant, long-haul shipping device.
As autonomous vehicles near commercial viability, Waymo’s procurement deal with Fiat Chrysler is just the beginning.
The exact value of this future automotive industry has yet to be defined, but research from Intel’s internal autonomous vehicle division estimates this new so-called “passenger economy” could be worth nearly $7 trillion a year. To position themselves to capture a chunk of this potential revenue, companies whose businesses used to lie in previously disparate fields such as robotics, software, ships, and entertainment (to name but a few) have begun to form a bewildering web of what they hope will be symbiotic partnerships. Car hailing and chip companies are collaborating with car rental companies, who in turn are befriending giant software firms, who are launching joint projects with all sizes of hardware companies, and so on.
Last year, car companies sold an estimated 80 million new cars worldwide. Over the course of nearly a century, car companies and their partners, global chains of suppliers and service providers, have become masters at mass-producing and maintaining sturdy and cost-effective human-driven vehicles. As autonomous vehicle technology becomes ready for mainstream use, traditional automotive companies are being forced to grapple with the painful realization that they must compete in a new playing field.
The challenge for traditional car-makers won’t be that people no longer want to own cars. Instead, the challenge will be learning to compete in a new and larger transportation industry where consumers will choose their product according to the appeal of its customized body and the quality of its intelligent software.
—
Melba Kurman and Hod Lipson are the authors of Driverless: Intelligent Cars and the Road Ahead and Fabricated: the New World of 3D Printing.
Image Credit: hfzimages / Shutterstock.com
We are a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for us to earn fees by linking to Amazon.com and affiliated sites. Continue reading
#431999 Brain-Like Chips Now Beat the Human ...
Move over, deep learning. Neuromorphic computing—the next big thing in artificial intelligence—is on fire.
Just last week, two studies individually unveiled computer chips modeled after information processing in the human brain.
The first, published in Nature Materials, found a perfect solution to deal with unpredictability at synapses—the gap between two neurons that transmit and store information. The second, published in Science Advances, further amped up the system’s computational power, filling synapses with nanoclusters of supermagnetic material to bolster information encoding.
The result? Brain-like hardware systems that compute faster—and more efficiently—than the human brain.
“Ultimately we want a chip as big as a fingernail to replace one big supercomputer,” said Dr. Jeehwan Kim, who led the first study at MIT in Cambridge, Massachusetts.
Experts are hopeful.
“The field’s full of hype, and it’s nice to see quality work presented in an objective way,” said Dr. Carver Mead, an engineer at the California Institute of Technology in Pasadena not involved in the work.
Software to Hardware
The human brain is the ultimate computational wizard. With roughly 100 billion neurons densely packed into the size of a small football, the brain can deftly handle complex computation at lightning speed using very little energy.
AI experts have taken note. The past few years saw brain-inspired algorithms that can identify faces, falsify voices, and play a variety of games at—and often above—human capability.
But software is only part of the equation. Our current computers, with their transistors and binary digital systems, aren’t equipped to run these powerful algorithms.
That’s where neuromorphic computing comes in. The idea is simple: fabricate a computer chip that mimics the brain at the hardware level. Here, data is both processed and stored within the chip in an analog manner. Each artificial synapse can accumulate and integrate small bits of information from multiple sources and fire only when it reaches a threshold—much like its biological counterpart.
Experts believe the speed and efficiency gains will be enormous.
For one, the chips will no longer have to transfer data between the central processing unit (CPU) and storage blocks, which wastes both time and energy. For another, like biological neural networks, neuromorphic devices can support neurons that run millions of streams of parallel computation.
A “Brain-on-a-chip”
Optimism aside, reproducing the biological synapse in hardware form hasn’t been as easy as anticipated.
Neuromorphic chips exist in many forms, but often look like a nanoscale metal sandwich. The “bread” pieces are generally made of conductive plates surrounding a switching medium—a conductive material of sorts that acts like the gap in a biological synapse.
When a voltage is applied, as in the case of data input, ions move within the switching medium, which then creates conductive streams to stimulate the downstream plate. This change in conductivity mimics the way biological neurons change their “weight,” or the strength of connectivity between two adjacent neurons.
But so far, neuromorphic synapses have been rather unpredictable. According to Kim, that’s because the switching medium is often comprised of material that can’t channel ions to exact locations on the downstream plate.
“Once you apply some voltage to represent some data with your artificial neuron, you have to erase and be able to write it again in the exact same way,” explains Kim. “But in an amorphous solid, when you write again, the ions go in different directions because there are lots of defects.”
In his new study, Kim and colleagues swapped the jelly-like switching medium for silicon, a material with only a single line of defects that acts like a channel to guide ions.
The chip starts with a thin wafer of silicon etched with a honeycomb-like pattern. On top is a layer of silicon germanium—something often present in transistors—in the same pattern. This creates a funnel-like dislocation, a kind of Grand Canal that perfectly shuttles ions across the artificial synapse.
The researchers then made a neuromorphic chip containing these synapses and shot an electrical zap through them. Incredibly, the synapses’ response varied by only four percent—much higher than any neuromorphic device made with an amorphous switching medium.
In a computer simulation, the team built a multi-layer artificial neural network using parameters measured from their device. After tens of thousands of training examples, their neural network correctly recognized samples 95 percent of the time, just 2 percent lower than state-of-the-art software algorithms.
The upside? The neuromorphic chip requires much less space than the hardware that runs deep learning algorithms. Forget supercomputers—these chips could one day run complex computations right on our handheld devices.
A Magnetic Boost
Meanwhile, in Boulder, Colorado, Dr. Michael Schneider at the National Institute of Standards and Technology also realized that the standard switching medium had to go.
“There must be a better way to do this, because nature has figured out a better way to do this,” he says.
His solution? Nanoclusters of magnetic manganese.
Schneider’s chip contained two slices of superconducting electrodes made out of niobium, which channel electricity with no resistance. When researchers applied different magnetic fields to the synapse, they could control the alignment of the manganese “filling.”
The switch gave the chip a double boost. For one, by aligning the switching medium, the team could predict the ion flow and boost uniformity. For another, the magnetic manganese itself adds computational power. The chip can now encode data in both the level of electrical input and the direction of the magnetisms without bulking up the synapse.
It seriously worked. At one billion times per second, the chips fired several orders of magnitude faster than human neurons. Plus, the chips required just one ten-thousandth of the energy used by their biological counterparts, all the while synthesizing input from nine different sources in an analog manner.
The Road Ahead
These studies show that we may be nearing a benchmark where artificial synapses match—or even outperform—their human inspiration.
But to Dr. Steven Furber, an expert in neuromorphic computing, we still have a ways before the chips go mainstream.
Many of the special materials used in these chips require specific temperatures, he says. Magnetic manganese chips, for example, require temperatures around absolute zero to operate, meaning they come with the need for giant cooling tanks filled with liquid helium—obviously not practical for everyday use.
Another is scalability. Millions of synapses are necessary before a neuromorphic device can be used to tackle everyday problems such as facial recognition. So far, no deal.
But these problems may in fact be a driving force for the entire field. Intense competition could push teams into exploring different ideas and solutions to similar problems, much like these two studies.
If so, future chips may come in diverse flavors. Similar to our vast array of deep learning algorithms and operating systems, the computer chips of the future may also vary depending on specific requirements and needs.
It is worth developing as many different technological approaches as possible, says Furber, especially as neuroscientists increasingly understand what makes our biological synapses—the ultimate inspiration—so amazingly efficient.
Image Credit: arakio / Shutterstock.com Continue reading