Sign up for our daily briefing

Make your busy days simpler with Axios AM/PM. Catch up on what's new and why it matters in just 5 minutes.

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Catch up on the day's biggest business stories

Subscribe to Axios Closer for insights into the day’s business news and trends and why they matter

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Stay on top of the latest market trends

Subscribe to Axios Markets for the latest market trends and economic insights. Sign up for free.

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Sports news worthy of your time

Binge on the stats and stories that drive the sports world with Axios Sports. Sign up for free.

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Tech news worthy of your time

Get our smart take on technology from the Valley and D.C. with Axios Login. Sign up for free.

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Get the inside stories

Get an insider's guide to the new White House with Axios Sneak Peek. Sign up for free.

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Catch up on coronavirus stories and special reports, curated by Mike Allen everyday

Catch up on coronavirus stories and special reports, curated by Mike Allen everyday

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Want a daily digest of the top Denver news?

Get a daily digest of the most important stories affecting your hometown with Axios Denver

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Want a daily digest of the top Des Moines news?

Get a daily digest of the most important stories affecting your hometown with Axios Des Moines

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Want a daily digest of the top Twin Cities news?

Get a daily digest of the most important stories affecting your hometown with Axios Twin Cities

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Want a daily digest of the top Tampa Bay news?

Get a daily digest of the most important stories affecting your hometown with Axios Tampa Bay

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Want a daily digest of the top Charlotte news?

Get a daily digest of the most important stories affecting your hometown with Axios Charlotte

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

Please enter a valid email.

Please enter a valid email.

Subscription failed
Thank you for subscribing!

The AI system operating in maze environments with partial information. Credit: DeepMind

A machine learning system from Google's DeepMind can collect snapshots of a 3D scene taken from different angles and then predict what that environment will look like from a viewpoint it hasn't seen before, according to research published today in Science.

The big picture: Researchers want to create AIs that can build models of the world from data they've seen and then use those models to function in new environments. That capability could take an AI from the realm of learning about a space to understanding it — much the same way humans do — and is key to developing machines that can move autonomously through the world. (Think: driverless cars.)

The context: Computer vision — spurred by the availability of data and increased computing power — has rapidly advanced in the past six years. Many of the underlying algorithms largely learn via supervision: an algorithm is given a large dataset that is labeled with information (for example, about the object in a scene) and uses it to predict an output.

“Supervised learning has been super successful but it’s unsatisfying for two reasons. One, humans need to manually create the [training] datasets, which is expensive and they don’t capture everything. And two, it is not the way infants or higher mammals learn.”
— Ali Eslami, study author and researcher at DeepMind

Instead, researchers want to train machines to learn from unlabeled inputs that they process without any guidance from a human, and then to be able to apply or transfer what they learn to other new scenarios and tasks.

How it works: The system uses a pair of images of a virtual 3D scene taken from different angles to create a representation of the space. A separate “generation” network then predicts what the scene will look like from a different viewpoint it hasn’t seen before.

  • After training the generative query network (GQN) on millions of images, it could use one image to determine the identity, position and color of objects as well as shadows and other aspects of perspective, the authors wrote.
  • That ability to understand the scene's structure is the "most fascinating" part of the study, wrote the University of Maryland's Matthias Zwicker, who wasn't involved in the research.
  • The DeepMind researchers also tested the AI in a maze and reported the network can accurately predict a scene with only partial information.
  • A virtual robotic arm could also be controlled by the GQN to reach a colored object in a scene.

Yes, but: These are relatively simple virtual environments and "it remains unclear how close [the researchers'] approach could come to understanding complex, real-world environments," Zwicker writes.

Harvard's Sam Gershman told MIT Technology Review the GQN still solves only the narrow problem of predicting what a scene looks like from a different angle. According to the article:

"Gershman says it’s unclear whether DeepMind’s approach could be adapted to answer more complex questions or whether some fundamentally different approach might be required."

The challenges: Eslami says it took a couple of months to train the network. “We really were pushing the hardware available to us to its limits. We need a step up in hardware capabilities and the techniques to build these deep neural networks and train them.”

Go deeper: Read more about the various ways researchers are trying to design AI to work like the human brain.

Go deeper

Bernie Madoff dies in prison at 82

Photo: Jin Lee/Bloomberg via Getty Images

Bernie Madoff, a former investor sentenced to 150 years in prison for perpetrating the largest Ponzi scheme in U.S. history, died Wednesday at age 82, AP reports.

The big picture: Madoff pleaded guilty in 2009 to a multibillion-dollar scheme that investigators said began in the 1970s and defrauded as many as 37,000 people in 136 countries — including high-profile victims like Steven Spielberg, former New York Mets owner Fred Wilpon and actor Kevin Bacon, according to CNBC.

Ben Geman, author of Generate
2 hours ago - World

John Kerry and China's long road ahead on climate

Photo illustration: Aïda Amer/Axios. Photo: Brian Snyder/AFP via Getty Images

Yes, special climate envoy John Kerry's really in China and no, don't look for a huge breakthrough between the world's two largest carbon-emitting nations.

Driving the news: The State Department yesterday announced Kerry's visit this week, confirming plans that began emerging Saturday.

2 hours ago - Podcasts

Coinbase president Emilie Choi on mainstreaming crypto

Coinbase plans to go public on Wednesday, in a watershed moment for the cryptocurrency industry.

Axios Re:Cap speaks with Coinbase president and COO Emilie Choi about how she thinks about crypto, why Coinbase eschewed a traditional IPO and if we’re ever going to use bitcoin to buy a cup of coffee.