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
Real Time with… IPC APEX EXPO 2024: The Driving World of e-Mobility with Indium
05/08/2024 | Real Time with...IPC APEX EXPOIn the competitive EV market, technology plays a crucial role facing the challenges of infrastructure. As Brian O'Leary explains, Indium's e-Mobility product suite includes proven solder and thermal management products for high reliability.
2024 Apple iPad Pro Estimated to Ship Between 4.5 to 5 Million Units
05/08/2024 | TrendForceApple’s recent product launch in May introduced a lineup of new tablets featuring advanced AMOLED screens. Notably, the Pro version boasts a dual-layer tandem structure designed to address the longstanding challenges of screen burn-in and lifespan that are common with AMOLED displays.
GPV's Handover of Refurbished Factory Building
05/07/2024 | GPVOn 6 May 2024, Bjorn Fiskers, MD at GPV Electronics TH in Thailand and his team were handed the keys to our refurbished factory building, adding another 7,000 sqm to our current 15,000 sqm electronics factory. Our electronics factory in Thailand will comprise of a total of 22,000 sqm.
Siemens Delivers New Solido IP Validation Suite
05/07/2024 | SiemensSiemens Digital Industries Software introduced Solido™ IP Validation Suite software, a comprehensive, automated signoff solution for quality assurance across all design intellectual property (IP) types, including standard cells, memories and IP blocks.
Hirose Launches Solution Partner Network to Address Changing Design Challenges
05/06/2024 | HiroseHirose, a leader in the design and manufacturing of innovative connector solutions, has established a Solution Partner Network that enables OEMs to quickly explore product design, specialty IP, and component fulfillment options that best suit their needs.