back to ideas for this text


Single Idea 19736

[from 'New Scientist articles' by New Scientist writers, in 15. Nature of Minds / C. Capacities of Minds / 3. Abstraction by mind ]

Full Idea

Early neural nets were really good at recognising general categories, such as a car or a chair. Those networks are good at extracting the 'chair-ness' or the 'car-ness' of the object.

Gist of Idea

Neural networks can extract the car-ness of a car, or the chair-ness of a chair

Source

New Scientist writers (New Scientist articles [2013], 2015.12.12)

Book Reference

-: 'New Scientist magazine' [ 2013], p.28


A Reaction

[Interview with Yann LeCun, Facebook AI director] Fregean philosophers such as Geach think that extracting features is a ridiculous idea, but if even a machine can do it then I suspect that human beings can (and do) manage it too.