(Beth J. Harpaz / AP)

Deep-learning algorithms can identify objects and faces better than humans in some cases but are limited in their ability to recognize amorphous forms, like grasses and trees, that can take different shapes and sizes and are continually changing. But a team, led by Takeshi Ise at the Kyoto University in Japan, has developed a new technique that will help machines overcome these limitations, per the MIT Technology Review. The method centers on teaching machines to recognize different types of moss, a plant that doesn't take a well-defined, distinctive shape.

Why it matters: The method could be used to better recognize trees and crops in aerial photos, which would be valuable for monitoring agriculture and for conservation and land management efforts.

How they did it: Ise and his team started by photographing three different types of moss, both individually and in places where they were grouped with other plants. They then worked to create an algorithm that could distinguish the different types of moss by meticulously labeling the different versions and feeding it into the deep-learning machine.

The results: The algorithm quickly learned to identify each type of moss when grouped among others in a single image. "The model correctly classified test images with accuracy more than 90%," the team said.

Limitations of study: The algorithm recognized some types of moss better than others. For example, the types of moss that are more amorphous with less defined forms of growth were harder to identify than those that had a more distinctive shape. But the team said they plan to continue improving the accuracy of their method by experimenting with how the photos are taken.

Go deeper

Congress' next moves to rein in Big Tech

Illustration: Eniola Odetunde/Axios

After grilling the CEOs of Amazon, Facebook, Google and Apple last week, members of Congress are grappling with whether to accuse any of the firms of illegal anticompetitive behavior, to propose updating federal antitrust laws — or both.

The big picture: Congress is just one arm of government making the case against these companies. Google is expected to be the first of the firms to face possible antitrust litigation from the Justice Department before summer's end, but all four face a full-court press of investigations by DOJ, the Federal Trade Commission and state attorneys general.

Fauci: Coronavirus task force to examine aerosolized spread


A sneeze. Photo: Maartje van Caspel/Getty Images

The White House coronavirus task force will examine more closely just how much SARS-CoV-2 might be transmitted via aerosols, and not just from droplets, NIAID director Anthony Fauci said Wednesday at an online forum sponsored by Harvard T.H. Chan School of Public Health.

Why it matters: The longer the coronavirus can remain infectious in the air, the more likely it can infect people, particularly indoors — leading to the possible need to alter air filtration and circulation within buildings.

The next wave to hit Main Street

Illustration: Eniola Odetunde/Axios

Call it the great retail wash. A wave of defaults, bankruptcies and evictions expected in cities across the U.S. is poised to remake the retail landscape across the country, but there may be some upside for consumers and small businesses.

Why it matters: Rather than an overnight descent into a collection of urban wastelands full of Starbucks, Amazon fulfillment centers, Chase bank branches and nothing else, the coronavirus pandemic and resulting retail apocalypse may just mean that, in major U.S. cities, less is more.