Machines that learn like people, MIT News

Image: MIT News
December 23, 2015

Algorithms could learn to recognize objects from a few examples, not millions; may better model human cognition.

Larry Hardesty | MIT News Office
December 23, 2015


An excerpt for the article:

"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. ..."