Hubert L. Dreyfus (2004)
"A Phenomenology of Skill Acquisition as the basis for a Merleau-Pontian Nonrepresentationalist
Cognitive Science."
http://web.archive.org/web/20061216075452/ist-socrates.berkeley.edu/~hdreyfus/pdf/MerleauPontySkillCogSci.pdf


Neural-network modelers agree that an intelligent network must be able to generalize.
...
If everything is similar to everything else in an indefinitely large number of ways, what constrains the space of possible generalizations so that trial and error learning has a chance of succeeding?