"The mechanism of learning is of course one of the most enthralling and baffling mysteries in the field of biology."

“Some of these patterns of performance were calculable, though only as types of behaviour, in advance; some were quite unforeseen.”

“These models are of course so simple that any more detailed comparison between them and living creatures would be purely conjectural.”

“because they illustrate particularly the exploratory, speculative behaviour that is so characteristic of most animals.”

“Not in looks, but in action, the model must resemble an animal. Therefore it must have these or some measure of these attributes: exploration, curiosity, free-will in the sense of unpredictability, goalseeking, self-regulation, avoidance of dilemmas, foresight, memory, learning, forgetting, association of ideas, form recognition, and the elements of social accommodation. Such is life.”

“Rapidly going over what I could recall of Jim Bursley's information about pathological curves confirmed the conjecture. The snowball curve, derived from an equilateral triangle, is a perimeter of infinite length enclosing a finite area. The angles or points of the perimeter are uncountable. An equilateral triangle projected integrally in the third dimension is a triangular pyramid of equal surfaces. The three-dimensional snowflake derived from this pyramid--hence its diamantine appearance--is a finite volume enclosed in a surface of infinite area. The convolutions of such a surface, to be gathered around its defined content extrude a number of discrete angles or points beyond all possibility of computation. The pressure on each point is infinitesimal, unmeasurably small; the total external pressure exerted on any part of the surface is an aggregate of infinitesimal values, itself infinitesimal.”

“The first notion of constructing a free goal-seeking mechanism goes back a wartime talk with the psychologist,, whose untimely death was one of the greatest losses Cambridge has suffered in years. When he was engaged on a warjob for the Government, he came to get the help of an automatic analyzer with some very complicated curves he had obtained, curves relating to the aiming errors of air gunners. Goal-seeking missiles were literally much in the air in those days; so, in our minds, were scanning mechanisms. Long before the home study was turned into a workshop, the two ideas, goal-seeking and scanning, had combined as the essential mechanical conception of a working model that would behave like a very simple animal.”