Object-recognition systems are beginning to get pretty good — and in the case of Facebook’s face-recognition algorithms, frighteningly good.
But object-recognition systems are typically trained on millions of visual examples, which is a far cry from how humans learn. Show a human two or three pictures of an object, and he or she can usually identify new instances of it.
Four years ago, Tomaso Poggio’s group at MIT’s McGovern Institute for Brain Research began developing a new computational model of visual representation, intended to reflect what the brain actually does. And in a forthcoming issue of the journal Theoretical Computer Science, the researchers prove that a machine-learning system based on their model could indeed make highly reliable object discriminations on the basis of just a few examples.
In both that paper and another that appeared in October in PLOS Computational Biology, they also show that aspects of their model accord well with empirical evidence about how the brain works.
“If I am given an image of your face from a certain distance, and then the next time I see you, I see you from a different distance, the image is quite different, and simple ways to match it don’t work,” says Poggio, the Eugene McDermott Professor in the Brain Sciences in MIT’s Department of Brain and Cognitive Sciences. “In order solve this, you either need a lot of examples — I need to see your face not only in one position but in all possible positions — or you need an invariant representation of an object.”
An invariant representation of an object is one that’s immune to differences such as size, location, and rotation within the lane. Computer vision researchers have proposed several techniques for invariant object representation, but Poggio’s group had the further challenge of finding an invariant representation that was consistent with what we know about the brain’s machinery.
Page 1 of 2
Suggested Items
Septentrio Expands UAV Ecosystem for Reliable GNSS Positioning
04/22/2024 | SeptentrioSeptentrio, a leader in high-precision GNSS* positioning solutions, is closely working with several major drone solutions providers including 3DR, Holybro, ARK Electronics and Systork, which is resulting in various new products that allow easier prototyping or integration of the mosaic™ GNSS receiver into UAVs.
Growth Potential: Electronics Manufacturing Driving Massive Surge in Manufacturing Investment
04/22/2024 | Shawn DuBravac, IPCIn the early months of the pandemic, investment in manufacturing infrastructure, such as plants and production facilities, declined sharply. Real investment dropped over 11%, before finally recovering to pre-pandemic levels in the first half of 2022. Over the past two years, however, several factors have combined to drive manufacturing investment to record levels.
ViTrox Pioneering the Future of Smart Manufacturing at NEPCON China 2024
04/18/2024 | ViTroxViTrox, which aims to be the World’s Most Trusted Technology Company, is pleased to announce its participation in the NEPCON China 2024 at Booth #1H27 at Shanghai World Expo Exhibition & Convention Center from 24-26 April 2024.
AIM to Highlight NC259FPA Ultrafine No Clean Solder Paste at SMTA Wisconsin Expo & Tech Forum
04/18/2024 | AIMAIM Solder, a leading global manufacturer of solder assembly materials for the electronics industry, is pleased to announce its participation in the upcoming SMTA Wisconsin Expo & Tech Forum taking place on May 7 at the Four Points by Sheraton | Milwaukee Airport, in Milwaukee, Wisconsin.
New Yorker, Geyer Electronic Sign New Distribution Agreement
04/16/2024 | New Yorker Electronics Co.New Yorker Electronics, global distributor of electronic components, recently announced a new franchised distribution agreement with Geyer Electronic. Geyer is an international manufacturer of Quart Crystals, Oscillators and Resonators.