Learning Representations that Support Extrapolation

Understand

Extrapolation -- the ability to make inferences that go beyond the scope of one's experiences -- is a hallmark of human intelligence.

• By contrast, the generalization exhibited by contemporary neural network algorithms is largely limited to interpolation between data points in their training corpora.
• In this paper, we consider the challenge of learning representations that support extrapolation.
• We introduce a novel visual analogy benchmark that allows the graded evaluation of extrapolation as a function of distance from the convex domain defined by the training data.