It would be as useless to perceive how things 'actually look' as it would be to watch the random dots on untuned television screens.

We wanted to solve robot problems and needed some vision, action, reasoning, planning, and so forth. We even used some structural learning, such as was being explored by Patrick Winston.

If we understood something just one way, we would not understand it at all.

A computer is like a violin. You can imagine a novice trying first a phonograph and then a violin. The latter, he says, sounds terrible. That is the argument we have heard from our humanists and most of our computer scientists. Computer programs are good, they say, for particular purposes, but they aren’t flexible. Neither is a violin, or a typewriter, until you learn how to use it.

But the big feature of human-level intelligence is not what it does when it is works but what it does when it's stuck.

When David Marr at MIT moved into computer vision, he generated a lot of excitement, but he hit up against the problem of knowledge representation; he had no good representations for knowledge in his vision systems.

You don't understand anything until you learn it more than one way.