NEIL program labels images, learns associations with minimal help from people
A computer program called the Never Ending Image Learner (NEIL) is running 24 hours a day at Carnegie Mellon University, searching the Web for images, doing its best to understand them on its own and, as it builds a growing visual database, gathering common sense on a massive scale.
NEIL leverages recent advances in computer vision that enable computer programs to identify and label objects in images, to characterize scenes and to recognize attributes, such as colors, lighting and materials, all with a minimum of human supervision. In turn, the data it generates will further enhance the ability of computers to understand the visual world.
But NEIL also makes associations between these things to obtain common sense information that people just seem to know without ever saying — that cars often are found on roads, that buildings tend to be vertical and that ducks look sort of like geese. Based on text references, it might seem that the color associated with sheep is black, but people — and NEIL — nevertheless know that sheep typically are white.
“Images are the best way to learn visual properties,” said Abhinav Gupta, assistant research professor in Carnegie Mellon’s Robotics Institute. “Images also include a lot of common sense information about the world. People learn this by themselves and, with NEIL, we hope that computers will do so as well.”
A computer cluster has been running the NEIL program since late July and already has analyzed three million images, identifying 1,500 types of objects in half a million images and 1,200 types of scenes in hundreds of thousands of images. It has connected the dots to learn 2,500 associations from thousands of instances.
The public can now view NEIL’s findings at the project website, http://www.neil-kb.com.
The research team, including Xinlei Chen, a Ph.D. student in CMU’s Language Technologies Institute, and Abhinav Shrivastava, a Ph.D. student in robotics, will present its findings on Dec. 4 at the IEEE International Conference on Computer Vision in Sydney, Australia.
One motivation for the NEIL project is to create the world’s largest visual structured knowledge base, where objects, scenes, actions, attributes and contextual relationships are labeled and catalogued.
“What we have learned in the last 5-10 years of computer vision research is that the more data you have, the better computer vision becomes,” Gupta said.
Some projects, such as ImageNet and Visipedia, have tried to compile this structured data with human assistance. But the scale of the Internet is so vast — Facebook alone holds more than 200 billion images — that the only hope to analyze it all is to teach computers to do it largely by themselves.
Shrivastava said NEIL can sometimes make erroneous assumptions that compound mistakes, so people need to be part of the process. A Google Image search, for instance, might convince NEIL that “pink” is just the name of a singer, rather than a color.
“People don’t always know how or what to teach computers,” he observed. “But humans are good at telling computers when they are wrong.”
People also tell NEIL what categories of objects, scenes, etc., to search and analyze. But sometimes, what NEIL finds can surprise even the researchers. It can be anticipated, for instance, that a search for “apple” might return images of fruit as well as laptop computers. But Gupta and his landlubbing team had no idea that a search for F-18 would identify not only images of a fighter jet, but also of F18-class catamarans.
As its search proceeds, NEIL develops subcategories of objects – tricycles can be for kids, for adults and can be motorized, or cars come in a variety of brands and models. And it begins to notice associations – that zebras tend to be found in savannahs, for instance, and that stock trading floors are typically crowded.
The Latest Google Headlines on:
Machine Learning
[google_news title=”” keyword=”Machine Learning” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
The Latest Bing News on:
Machine Learning
- New machine learning algorithm promises advances in computingon May 9, 2024 at 3:03 pm
Systems controlled by next-generation computing algorithms could give rise to better and more efficient machine learning products, a new study suggests.
- Machine learning tool flags undiagnosed immunodeficiency diseaseon May 9, 2024 at 6:00 am
A machine learning model can effectively sift through EHR data to rank patients' likelihood of having common variable immunodeficiency disease.
- Five Takeaways: Artificial Intelligence & Machine Learningon May 9, 2024 at 12:00 am
The Journal of Business hosted Yanek Kondryszyn, intellectual property attorney and partner at Lee & Hayes PLLC, for its most recent Elevating The Conversation podcast.
- Machine Learning Takes the Stage at TC Sessions: Robotics+AIon May 8, 2024 at 2:00 pm
The roots of machine learning go back at least to 1962, when Doug Engelbart of the Stanford Research Institute argued that computers could play a role in augmenting the human intellect. Outlandish at ...
- Machine learning aids in discovery of sperm whale ‘alphabet’on May 8, 2024 at 11:01 am
Researchers at MIT CSAIL and Project CETI believe that they have unlocked a kind of sperm whale alphabet with the aid of machine learning technologies.
- The Future Of SEO: How AI And Machine Learning Are Changing Searchon May 8, 2024 at 4:45 am
Despite the uncertainty about how search engines adjust to the new AI world, machine learning is revolutionizing—for the better—the way businesses approach SEO.
- From Beginner To Enthusiast: Top 5 Free Harvard Courses To Spark Your AI Journey With Machine Learning, Python And Moreon May 8, 2024 at 3:55 am
Ever thought about diving into the world of Artificial Intelligence (AI) but felt intimidated by the hefty price tags on courses? Well, Harvard University is offering a golden opportunity to get ...
- Machine learning helps to discover sperm whale ‘alphabet'on May 8, 2024 at 3:07 am
Researchers have cracked the code to a sperm whale ‘alphabet' after using machine learning technologies to understand vocalizations. In a… Continue reading Machine learning helps to discover sperm ...
- Machine learning engineer salary: How much do AI techs make?on May 7, 2024 at 4:02 pm
Machine learning engineers tend to be among the highest-paid employees in tech. Here’s how much they make and which companies pay the most.
- Tomorrow’s physics test: machine learningon May 7, 2024 at 7:20 am
Machine learning is becoming an essential part of a physicist’s toolkit. How should new students learn to use it?
The Latest Google Headlines on:
Never Ending Image Learner
[google_news title=”” keyword=”Never Ending Image Learner” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
The Latest Bing News on:
Never Ending Image Learnerb
- KOREA: The Never-Ending Waron April 28, 2024 at 5:00 pm
Shedding new light on a geopolitical hot spot, the film — written and produced by John Maggio and narrated by Korean-American actor John Cho — confronts the “Forgotten War” perception of ...
- Overcoming Finnish language fears one step at a time — "If you don't speak, you won't learn"on April 26, 2024 at 6:17 am
Despite having a reputation for being very difficult, many immigrants to Finland find their own path to learning the Finnish language.
- Martha Stewart Has ‘Never-Ending Curiosity’ (And a Few Regrets.)on April 16, 2024 at 11:22 am
Here, in 1976, she chopped vegetables in her kitchen. Arthur Schatz/Getty Images In 1980, she lived in Connecticut with her then husband, Andy Stewart. Her first book, “Entertaining,” was ...
- I’ll never get the image of my naked dad in Race Across the World out of my headon April 11, 2024 at 5:19 am
The image of him sat, naked perched atop a stool ... I get to really see, completely unfiltered, who he is in a way I’ve never seen before. We will all have found ourselves in situations after ...
- Never-ending insurgencyon April 6, 2024 at 5:00 pm
THE insurgency in Balochistan has entered its third phase. The insurgents have intensified their terrorist attacks against the security forces, Chinese interests, and those nationalist actors who ...
- Never Ending Dungeonon April 6, 2024 at 3:38 pm
All the Latest Game Footage and Images from Never Ending Dungeon Never Ending Dungeon is AI-powered software to adventures creation for Tabletop RPGs. Less prep, more play. A huge time saver for ...
- Never-ending backlog predicted as 5m learner drivers fight for 1.8m driving test slots in 2024on February 18, 2024 at 4:00 pm
Frustrated learner drivers seeking to book driving tests ... The firm has warned that “the backlog might never end if capacity in the testing system doesn’t increase”. Breaking down the ...
- Olive Garden’s Never Ending Pasta Bowl Is Coming Backon September 22, 2023 at 12:46 pm
Some 30 years later, Olive Garden can still recreate that baffling kind of excitement with their annual Never Ending Pasta Bowl offer. This year, diners can load up on bowls brimming with angel ...
- AI Is Generating A Surreal, Endless Episode Of ‘Seinfeld’ On Twitchon February 2, 2023 at 9:45 am
I write about film, television, internet culture, and other fun stuff. The never-ending episode is, as its title suggests, very much “about nothing,” as algorithmically animated Seinfeld ...
- The CNN 10: Ideason April 3, 2022 at 10:56 am
The Never Ending Image Learner ("NEIL" to its friends) looks at millions of images on the Web, identifying and labeling them. For example, it might recognize a famous building, an animal's eye or ...