The Paper That Taught Neural Networks to Learn Backwards

Last week I read the 1958 Rosenblatt paper. The one that started everything. The Perceptron, the first learning machine, the idea that memory lives in connections and not addresses. And at the very end of that paper, almost as a footnote, Rosenblatt wrote that "some system, more advanced in principle than the perceptron, seems to be required." This is that system. Rumelhart, Hinton, and Williams. 1986. Four pages in Nature. And somewhere in those four pages, the answer to the question Rosenblatt