A team of researchers from MIT has used machine learning to develop a new computational model of the human brain's face-recognition mechanism.The system was trained to recognize particular faces by feeding it a battery of sample images. The scientists found that the trained system included an intermediate processing step that represented a face's degree of rotation – say, 45 degrees from centre – but not the direction – left or right, reports MIT News.Rather than a feature built into the system, this emerged spontaneously from the training process.Crucially, the team says that this means it duplicates an experimentally observed feature of the primate face-processing mechanism. The researchers consider this an indication that their system and the brain are doing something similar.”This is not a proof that we understand what's going on,” says Tomaso Poggio, a professor of brain and cognitive sciences at MIT and director of the Center for Brains, Minds, and Machines (CBMM), a multi-institution research consortium funded by the National Science Foundation and headquartered at MIT. “Models are kind of cartoons of reality, especially in biology. So I would be surprised if things turn out to be this simple. But I think it's strong evidence that we are on the right track.”Christof Koch, president and chief scientific officer at the Allen Institute for Brain Science, said this discovery is a step forward. “In this day and age, when everything is dominated by either big data or huge computer simulations, this shows you how a principled understanding of learning can explain some puzzling findings,” Koch said.Poggio has said before that the brain must produce “invariant” representations of faces and other objects, meaning representations that are indifferent to objects' orientation in space, their distance from the viewer, or their location in the visual field.Magnetic resonance scans of human and monkey brains suggested as much, but in 2010, Freiwald published a study describing the neuroanatomy of macaque monkeys' face-recognition mechanism in much greater detail.
Recent Video
- New non-profit trade association of HAND will standardise global talent ID
- No cards, no phones: J.P. Morgan’s biometric revolution in payments
- Anthony Vidiano on building the future of access management
- Charisma Check wins 2025 Start-Up Pitching Competition, advancing identity verification and background checks for dating app users
- How to protect one billion Amazon customers: Lessons from continuous risk assessments
