neural networks are made up of vast arrays of numbers, virtually none of which make intuitive sense to ordinary human beings.

SLAM,

Any theory that proposes to reduce intelligence down to a single principle—or a single “master algorithm”—is bound to be barking up the wrong tree.

To get there, we will need something else too: a fundamental rethinking of how learning works.

Deep learning is opaque.

No fact is an island.

In the language of cognitive psychology, what you do when you read any text is to build up a cognitive model of the meaning of what the text is saying. This can be as simple as compiling what Daniel Kahneman and the late Anne Treisman called an object file—a record of an individual object and its properties—or as complex as a complete understanding

learning but poor at compositionality and the construction of cognitive models; the other, classical AI, incorporates compositionality and the construction of cognitive models, but is mediocre at best at learning.

the boundaries are much vaguer.