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.

This is a tricky domain because, unlike simple arithmetic, to solve a calculus problem - and in particular to perform integration - you have to be smart about which integration technique should be used: integration by partial fractions, integration by parts, and so on.

If you just have a single problem to solve, then fine, go ahead and use a neural network. But if you want to do science and understand how to choose architectures, or how to go to a new problem, you have to understand what different architectures can and cannot do.

There was a failure to recognize the deep problems in AI; for instance, those captured in Blocks World. The people building physical robots learned nothing.

There are three basic approaches to AI: Case-based, rule-based, and connectionist reasoning.

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.

Once when I was standing at the base, they started rotating the set and a big, heavy wrench fell down from the 12 o'clock position of the set, and got buried in the ground a few feet from me. I could have been killed!

In general we are least aware of what our minds do best.

I heard that the same thing occurred in a scene in Alien, where the creature pops out of the chest of a crewman. The other actors didn't know what was to happen; the director wanted to get true surprise.

By the way, it was his simulations that helped out in Jurassic Park - without them, there would have been only a few dinosaurs. Based on his techniques, Industrial Light and Magic could make whole herds of dinosaurs race across the screen.

The basic idea in case-based, or CBR, is that the program has stored problems and solutions. Then, when a new problem comes up, the program tries to find a similar problem in its database by finding analogous aspects between the problems.

No computer has ever been designed that is ever aware of what it's doing; but most of the time, we aren't either.

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.

I think Lenat is headed in the right direction, but someone needs to include a knowledge base about learning.

Around 1967 Dan Bobrow wrote a program to do algebra problems based on symbols rather than numbers.

Societies need rules that make no sense for individuals. For example, it makes no difference whether a single car drives on the left or on the right. But it makes all the difference when there are many cars!

Kubrick's vision seemed to be that humans are doomed, whereas Clarke's is that humans are moving on to a better stage of evolution.

Stanley Kubrick knew we had good graphics around MIT and came to my lab to find out how to do it. We had some really good stuff. I was very impressed with Kubrick; he knew all the graphics work I had ever heard of, and probably more.

I believed in realism, as summarized by John McCarthy's comment to the effect that if we worked really hard, we'd have an intelligent system in from four to four hundred years.

Artificial intelligence is the science of making machines do things that would require intelligence if done by men.

I'm thinking of going to programming school. Learn how to sit down at any computer and learn to do anything on it. That's all I have left and have interest in.

I said, 'Okay, it's the year 2000, I'm getting a computer and a Palm Pilot.' I know how to check my e-mail, and I've listed some phone numbers on it. Half the time the battery has gone out so I can't use it.

To better understand why you need a personal computer, let's take a look at the pathetic mess you call your life.

I've got a computer, but I won't go near it.

All sorts of computer errors are now turning up. You'd be surprised to know the number of doctors who claim they are treating pregnant men.

All we can do when we think of kids today is think of more hours of school, earlier age at the computer, and curfews. Who would want to grow up in that world?

In OK Computer, the guitar was already moving towards a tone generator as well as a riff generator.

If you put garbage in a computer nothing comes out but garbage. But this garbage, having passed through a very expensive machine, is somehow ennobled and none dare criticize it.

Then in my early teens, when the home computer bubble was blowing, I had one of the first, an Acorn Atom, and used to write primitive adventures on that.

I compose my own stuff. I've been writing songs with words. I've been playing more on the keyboard because I can transpose it to sheet music on the computer.

I always say that my favorite game was Original Adventure, published by both Microsoft and Apple Computer back in 1980.

To err is human - and to blame it on a computer is even more so.

I think computer science, by and large, is still stuck in the Modern age.

It would be nice to design a real briefcase - you open it up and it's your computer but it also stores your books.

I am the farthest thing from a computer genius.

I wish I could have 25,000 years of my personal family history documented in a very powerful computer or a CD-ROM that I could just pop in and my computer would never crash.

The basis of computer work is predicated on the idea that only the brain makes decisions and only the index finger does the work.

In my second year in graduate school, I took a computer course and that was like lightening striking.

Some people may have noticed the new computer shelf at the anchor desk. Rather than phone calls, we want to take real time e-mails, and we'll be starting that very soon.

The cloning of humans is on most of the lists of things to worry about from Science, along with behaviour control, genetic engineering, transplanted heads, computer poetry and the unrestrained growth of plastic flowers.

The fact that biological, or "natural" rules might help in the creation of a computer generated work of art is interesting, but even a wonderful work of art made in this fashion isn't the same as a person, with all his or her experiences and emotions involved, making art.

Computer modelling for weather forecasting, and indeed for climate forecasting, has reached its limits.

The computer can't tell you the emotional story. It can give you the exact mathematical design, but what's missing is the eyebrows.

I have a son, Mason, who is disabled - cerebral palsy - and he does not walk independently, sit independently or speak. He uses a talking computer. I started becoming an advocate for him when he was 3 years old.

At the risk of being a fuddy-duddy I don't have a computer; I don't have e-mail; and I really don't need something in my house that I would be sitting in front of for hours.

A graphic representation of data abstracted from the banks of every computer in the human system. Unthinkable complexity. Lines of light ranged in the nonspace of the mind, clusters and constellations of data. Like city lights, receding.

Stories where the author has known very little, but run a computer program that tells him how to construct a planet, and looked up specific things about rocketry and so on, really suck.

Never ask what sort of computer a guy drives. If he's a Mac user, he'll tell you. If not, why embarrass him?