SEP 21, 2022 10:00 AM PDT

Researchers Examine "Black Box" of Artificial Intelligence

Credit: Pixabay

In a recent paper presented at the Conference on Uncertainty in Artificial Intelligence, a team of researchers from the Los Alamos National Laboratory in New Mexico has developed a new method for comparing neural networks that observes what’s known as the “black box” of artificial intelligence (AI). This study holds the potential to assist researchers to better understand the behavior of neural networks, which can be found in everyday devices from self-driving cars to facial recognition systems to virtual assistants.

"The artificial intelligence research community doesn't necessarily have a complete understanding of what neural networks are doing; they give us good results, but we don't know how or why," said Haydn Jones, a researcher in the Advanced Research in Cyber Systems group at Los Alamos, and lead author of the study. "Our new method does a better job of comparing neural networks, which is a crucial step toward better understanding the mathematics behind AI." Along with examining network similarity, the study marks an important step towards distinguishing the behavior of robust neural networks.

While neural networks exhibit high performance, they are also fragile. As an example, neural networks within self-driving cars are used to detect signs, which they do well under ideal conditions. However, even the smallest aberration—a sticker on a stop sign—might cause the network to misidentify the sign and not stop the car.

To refine neural networks, the research team is examining ways to improve the network’s robustness, which includes “attacking” the networks during their training process. This is done by introducing aberrations and then training the AI to ignore them, a process dubbed adversarial training which fundamentally makes it more difficult to fool the networks.

"We found that when we train neural networks to be robust against adversarial attacks, they begin to do the same things," said Jones. "By finding that robust neural networks are similar to each other, we're making it easier to understand how robust AI might really work. We might even be uncovering hints as to how perception occurs in humans and other animals.”

Sources: Conference on Uncertainty in Artificial Intelligence

As always, keep doing science & keep looking up!

About the Author
MS in Geological Sciences
Laurence Tognetti is a six-year USAF Veteran who earned both a BSc and MSc from the School of Earth and Space Exploration at Arizona State University. Laurence is extremely passionate about outer space and science communication, and is the author of “Outer Solar System Moons: Your Personal 3D Journey”.
You May Also Like
OCT 13, 2022
Technology
Four-Legged Robots Allowed to Run in The Wild Thanks to New Algorithms
OCT 13, 2022
Four-Legged Robots Allowed to Run in The Wild Thanks to New Algorithms
In a recent study that will be presented at the 2022 International Conference on Intelligent Robots and Systems (IROS) i ...
OCT 13, 2022
Technology
Robotic Pill Effective for Oral Delivery of Medications Like Insulin
OCT 13, 2022
Robotic Pill Effective for Oral Delivery of Medications Like Insulin
Treating and managing diabetes can be a lot of work, and it’s a condition that affects about 10% of Americans to d ...
OCT 21, 2022
Neuroscience
Telemental Health Services May Enforce Existing Healthcare Inequalities
OCT 21, 2022
Telemental Health Services May Enforce Existing Healthcare Inequalities
Telemental health services may not benefit everyone equally. The corresponding study was published in the Interactive Jo ...
OCT 21, 2022
Chemistry & Physics
Leaving Fossil Fuels in the Dust: Racing Company Licenses Quick-Fast Charging Batteries for Cars
OCT 21, 2022
Leaving Fossil Fuels in the Dust: Racing Company Licenses Quick-Fast Charging Batteries for Cars
Marc-Antoni Racing Corp. company has licensed a group of quick-charging batteries developed by the Oak Ridge National Li ...
NOV 16, 2022
Earth & The Environment
New Details About Earth's First Mass Extinction Unveiled by Geobiologists
NOV 16, 2022
New Details About Earth's First Mass Extinction Unveiled by Geobiologists
In a recent study published in the Proceedings of the National Academy of Sciences, a team of researchers led by Virgini ...
NOV 18, 2022
Technology
Inducing Hibernation Could Protect Living Organisms from Cosmic Radiation
NOV 18, 2022
Inducing Hibernation Could Protect Living Organisms from Cosmic Radiation
While many animals hibernate (called a state of torpor) on a seasonal basis, they often do it for a singular purpose: to ...
Loading Comments...