Machine learning, machine vision, and the brain

The problem of learning is arguably at the very core of the problem of inte lligence, both biological and artificial. In this article, we review our wo rk over the last 10 years in the area of supervised learning, focusing on t hree interlinked directions of research-(1) theory, (2) engineering applica tions (making intelligent software), and (3) neuroscience (understanding th e brain's mechanisms of learnings)-that contribute to and complement each o ther.