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
Taiflex Announces Grand Opening of Thailand Factory
05/17/2024 | TAIFLEX Scientific Co. LtdTaiflex Scientific Co., Ltd., a global leader in advanced flexible printed circuit (FPC) materials, held the grand opening ceremony of its Thailand factory at the Amata City Chonburi Industrial Estate in Chonburi, Thailand.
Shipments of OLED Monitors Hit 200,000 Units in 1Q24, Annual Forecast to Reach 1.34 Million
05/17/2024 | TrendForceTrendForce’s latest report reveals a robust start to 2024 for OLED monitors, with shipments reaching approximately 200,000 units in the first quarter—marking a YoY growth of 121%.
TRI Opens New Manufacturing Facility
05/16/2024 | TRITest Research, Inc. (TRI), the leading test and inspection systems provider for the electronics manufacturing industry, announced that it has opened a state-of-the-art R&D and manufacturing facility.
Real Time with… IPC APEX EXPO 2024: Manufacturing Intelligence from the Factory Floor
05/15/2024 | Real Time with...IPC APEX EXPONolan Johnson and Ranjan Chatterjee, Vice President of Smart Factory Business Units at PDF Solutions, discuss the background of Cimetrix and PDF Solutions. They explore the analytics tools provided by PDF Solutions, the merging of semiconductor and electronics manufacturing, and data handling in these industries. They also discuss different product lines, standards, packaging technologies, data usage, and integration with ERP systems
Foxconn Announces Q1 2024 Financial Results
05/14/2024 | Foxconn ElectronicsIn the January-March quarter revenue hit NT$1.324 trillion, with key profit margins all improving. Earnings per share for the first three months of 2024 reached NT$1.59.