Educability as a Technological Proposal

We seek to define the capability that has enabled humans to develop the civilization we have, and that distinguishes us from other species. “Intelligence” does not work here because we have no agreed definition of what intelligence is or how an intelligent entity behaves. We need a concept that is behaviorally better defined. The definition will need to be computational in the sense that the expected outcomes of exercising the capability need to be both specifiable and computationally feasible. This formulation is related to the goals of artificial intelligence research but is not synonymous with it, leaving out many capabilities we share with other species.

We make a proposal for this essential human capability and call it “educability.” It synthesizes abilities to learn from experience, to learn from others, and to chain together what we have learned in either mode and apply that to particular situations. It starts with the now standard notion of learning from examples as captured by the Probably Approximately Correct model and successfully used in machine learning. The question is how to round out this notion in order to capture the general human capability for absorbing and using information from the environment.

Since educability is defined in computational terms it constitutes a feasible goal for computer technology. We will describe the implications, challenges and possible next steps.

Speaker: Leslie Valiant, Harvard University