Images that humans perceive as completely unrelated can be classified as the same by computational models.
Caption:MIT neuroscientists have found that computational models of hearing and vision can build up their own idiosyncratic “invariances” — meaning that they respond the same way to stimuli with very different features. Credit: MIT News It is believed that when the human sensory system performs this kind of classification, it learns to disregard features that aren’t relevant to an object’s core identity, such as how much light is shining on it or what angle it’s being viewed from. This is known as invariance, meaning that objects are perceived to be the same even if they show differences in those less important features.
They term these stimuli “model metamers,” reviving an idea from classical perception research whereby stimuli that are indistinguishable to a system can be used to diagnose its invariances. The concept of metamers was originally developed in the study of human perception to describe colors that look identical even though they are made up of different wavelengths of light.
“The key inference from that is that these models seem to have what we call idiosyncratic invariances,” McDermott says. “They have learned to be invariant to these particular dimensions in the stimulus space, and it’s model-specific, so other models don’t have those same invariances.”
Technology Technology Latest News, Technology Technology Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: SciTechDaily1 - 🏆 84. / 68 Read more »