Skip to main content

An optimized solution for face recognition

When artificial intelligence is tasked with visually identifying objects and faces, it assigns specific components of its network to face recognition — just like the human brain.
  • Photo of a woman's face with reference points connected by lines
    Neuroscientists at MIT’s McGovern Institute have found that a computational network trained to identify faces and other objects discovers a surprisingly brain-like strategy to sort them all out.
    McGovern Institute

Professor Nancy Kanwisher and colleagues have published a paper in Science Advances, reporting on their findings on the functional specialization of regions of the human brain and that this specialization has similarities to computational networks.

In the paper they explain that "networks trained on object recognition perform poorly on face recognition and vice versa and that networks optimized for both tasks spontaneously segregate themselves into separate systems for faces and objects. We then show functional segregation to varying degrees for other visual categories, revealing a widespread tendency for optimization (without built-in task-specific inductive biases) to lead to functional specialization in machines and, we conjecture, also brains."