- New computer chip is inspired by the brains of insects like bees and flies
- Neuromorphic chip design can learn independently and adapt to extreme environments like deep space
- Tungsten-aluminum oxide nanocomposite allows chip to operate at power levels below one watt
Space. The final frontier. And on Nov. 2, 2018, NASA’s Voyager 2 spacecraft crossed into the vastness of interstellar space. Since its launch in 1977, the probe has traveled more than 11 billion miles across the solar system.
Powered by plutonium and drawing 400 watts of power to run its electronics and heat, the probe still snaps photos and sends them back to NASA. After 42 years, though, only six of Voyager 2’s ten instruments still work, and the probe is expected to go dark in 2025.
But what if Voyager 2 needed only a couple of watts of power? Could it survive long enough to continue its explorations far into the future?
These are the questions that scientists are asking at Argonne National Laboratory. Here, Angel Yanguas-Gil, principal materials scientist in the Applied Materials division, is leading an interdisciplinary team that is rethinking the design of computer chips to not only perform and adapt better, but to do so using a minuscule amount of power—around one watt.
For inspiration, the team is looking to the brains of insects, such as ants, bees, and fruit flies—which offer a new frontier in a type of artificial intelligence known as neuromorphic computing. What they have found could turn artificial intelligence (AI) on its artificial head.
Inspired by biology, the newly designed computer chips, which rely on new blueprints and materials, can bypass the “cloud” to learn on the fly, radically conserve power and adapt to extreme environments, such as deep space and radioactive areas—all while delivering reliable, accurate results.
The soft underbelly of artificial intelligence
Artificial intelligence pervades our lives, powering voice-activated digital assistants, guiding self-driving cars, and helping us automatically respond to emails. AI, however, has limitations: it relies on reams of data, and its ever-faster hardware demands a great deal of power and has limited flexibility.
For example, most neural networks, which uncover patterns and relationships in data without explicit programming, are designed for a specific task, such as recognizing images. Once a network learns that task, it can’t switch gears and start driving a car.
Insects, on the other hand, are versatile and can solve problems in different ways, said Yanguas-Gil.
“In a biological system, the network can learn by itself and offers a much higher degree of flexibility,” he said. “Evolutionary pressure on insects produces very efficient, adaptive computing machines.”
Accurate under pressure
To prove this point, Yanguas-Gil and Argonne chemists Jeff Elam and Anil Mane designed and simulated a new neuromorphic chip inspired by the tiny brain structure of bees, fruit flies, and ants. The network they created from scratch contains two pivotal discoveries:
- Dynamic filters and weights that change the strength of various neural connections, depending on what the system finds important in real time.
- Tungsten‐aluminum oxide, an award-winning nanocomposite material created by Elam and Mane, allows the chip to operate at power levels far below one watt. (Graphics processing units (GPUs), based on conventional silicon semiconductor processing, can consume >100 watts per chip.)
The new chip design is as accurate as the standard design, but it learned much more quickly and retained its accuracy—even under 60 percent error rates in its internal operation.
“With neural networks, error rates of 20 percent erode the system’s accuracy,” said Yanguas-Gil. “Our system can tolerate much higher error rates and sustain the same accuracy as a perfect system. This makes it a good candidate for machines that spend 30 years in space.”
Building the hive mind
After his team developed the blueprint for the neuromorphic chip, Yanguas-Gil enlisted Sandeep Madireddy and Prasanna Balaprakash, computer scientists in Argonne’s Mathematics and Computer Science (MCS) division tapped Argonne’s powerful computing tools to maximize its performance.
Using the Theta supercomputer, the duo ran the neuromorphic blueprint through a software package they developed called DeepHyper, which performs automated machine learning for neural networks. DeepHyper tests thousands of different insect brain configurations, generating better variations until it identifies the right one for a particular task.
With each set of configurations, DeepHyper learns. “It works in much the same way humans learn to play a game,” said Balaprakash. “You play, you get a score, and then—based on the feedback and your mistakes—you slowly get better and better.”
In a production scenario, all of this learning will be encoded onto the neuromorphic chip, and the chip itself will be able to adapt, shifting gears to solve each type of task.
How to change the game
Once Yanguas-Gil and his team uncover the best-performing chip design, they must agree on its best uses. What if, for instance, scientists could place low-power sensors in national forests to act as an alert for wildfires?
Or the chip might monitor urban areas for potential dangerous chemicals. Argonne has already installed 120 smart sensing devices around the city of Chicago to measure air quality, traffic, and climate.
These smart devices use Argonne’s Waggle technology platform, which includes remotely programmable high performance computing devices so that AI capabilities can be embedded with the sensors.
“Imagine if those sensors could learn in real time and detect poisonous gas?” asked Balaprakash.
These neuromorphic chips could act as mass spectrometers to learn in real time to recognize different molecule fragments without being explicitly programmed. “That would be a game changer,” says Yanguas-Gil.