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
Sypris Receives New Releases Under Electronic Warfare Program
05/03/2024 | Sypris Electronics LLCSypris Electronics, LLC, a subsidiary of Sypris Solutions, Inc., announced that it has recently received additional releases under a multi-year production contract that was first announced in 2022. The order, which provides for Sypris to begin deliveries in 2024, calls for the manufacture and test of electronic assemblies for an additional four systems to be supplied to a U.S. DOD contractor.
Gstar Announced the Strategic Move: Groundbreaking of Silicon Wafer Factory Construction in Indonesia
05/03/2024 | PRNewswireRecently, Gstar held a groundbreaking ceremony for its silicon rod and silicon wafer factory, marking the beginning of the rapid construction phase.
LQDX Divests Aluminum Soldering Business - Mina™ - to Taiyo America Inc.
05/02/2024 | PRNewswireLQDX, formerly known as Averatek Corp., developer of high-performance materials for advanced semiconductor manufacturing, today announced that it has divested its aluminum soldering business – known as MinaTM – to Taiyo America Inc., a global market leader in advanced electronic materials.
GPV’s Q1 2024 Interim Financial Report Shows Strong Navigation in Uncertain Times
05/01/2024 | GPVDanish-based GPV recorded an expected drop in sales to DKK 2.3 billion for the first quarter of 2024. The decline also affected the operating profit, which was DKK 155 million compared to DKK 179 million in the same quarter last year, although the EBITDA margin was maintained. In general, demand has been softer in 2024, but GPV continues to invest for the long-term and expects the trend to turn in the second half of 2024.
Europlacer Presents New Range of iineo SMT Placement Machines.
05/01/2024 | EuroplacerFor more than 15 years, the Europlacer iineo placement machines have made their mark on the SMT industry with unique features and unrivalled flexibility. Today, Europlacer announces the launch of the second generation iineo.