Marvin Minsky

If you understand something in only one way, then you don't really understand it at all. The secret of what anything means to us depends on how we've connected it to all other things we know. Well-connected representations let you turn ideas around in your mind, to envision things from many perspectives until you find one that works for you. And that's what we mean by thinking!

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.

You don't understand anything unless you understand there are at least 3 ways.

I think every person either inherits or eventually makes up their own idea of what they are and who they are and what caused the world to be, and it seems to me that these stories of creation myth, adopted by different cultures - most of them are less insightful than the stories made up by individual poets and writers.

I believe that everyone has to construct a mental model of what they are and where they came from and why they are as they are, and the word soul in each person is the name for that particular mish-mash of those fully formed ideas of one's nature.

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.

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

We all admire great accomplishments in the sciences, arts, and humanities - but we rarely acknowledge how much we achieve in the course of our everyday lives.

We humans are not the end of evolution, so if we can make a machine that's as smart as a person, we can probably also make one that's much smarter. There's no point in making just another person. You want to make one that can do things we can't.

Sometimes a problem will seem completely insurmountable. Then someone comes up with a simple new idea, or just a rearrangement of old ideas, that completely eliminates it.

Logic doesn't apply to the real world. D. R. Hofstadter and D. C. Dennett (eds.) The Mind's I, 1981.

Common sense is not a simple thing. Instead, it is an immense society of hard-earned practical ideas - of multitudes of life-learned rules and exceptions, dispositions and tendencies, balances and checks.

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.

What magical trick makes us intelligent? The trick is that there is no trick. The power of intelligence stems from our vast diversity, not from any single, perfect principle.

Logic doesn't apply to the real world.

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!

But just as astronomy succeeded astrology, following Kepler's discovery of planetary regularities, the discoveries of these many principles in empirical explorations of intellectual processes in machines should lead to a science, eventually.

Everything, including that which happens in our brains, depends on these and only on these: A set of fixed, deterministic laws.

Each part of the mind sees only a little of what happens in some others, and that little is swiftly refined, reformulated and "represented." We like to believe that these fragments have meanings in themselves - apart from the great webs of structure from which they emerge - and indeed this illusion is valuable to us qua thinkers - but not to us as psychologists - because it leads us to think that expressible knowledge is the first thing to study.

It makes no sense to seek a single best way to represent knowledge-because each particular form of expression also brings its particular limitations. For example, logic-based systems are very precise, but they make it hard to do reasoning with analogies. Similarly, statistical systems are useful for making predictions, but do not serve well to represent the reasons why those predictions are sometimes correct.