display all the ideas for this combination of texts
2 ideas
| 19736 | Neural networks can extract the car-ness of a car, or the chair-ness of a chair [New Sci.] |
| 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. | |
| From: New Scientist writers (New Scientist articles [2013], 2015.12.12) | |
| 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. |
| 8329 | Either causal relations are given in experience, or they are unobserved and theoretical [Sosa/Tooley] |
| Full Idea: There is a fundamental choice between the realist approach to causation which says that the relation is immediately given in experience, and the view that causation is a theoretical relation, and so not directly observable. | |
| From: E Sosa / M Tooley (Introduction to 'Causation' [1993], §1) | |
| A reaction: Even if immediate experience is involved, there is a step of abstraction in calling it a cause, and picking out events. A 'theoretical relation' is not of much interest there if no observations are involved. I don't think a choice is required here. |