RECOGNITION BY INFERENCE
| Collection | International Encyclopedia of Systems and Cybernetics |
|---|---|
| Year | 2004 |
| Vol. (num.) | 2(2) |
| ID | ◀ 2746 ▶ |
| Object type | Discipline oriented, Epistemology, ontology or semantics |
The capability to recognize patterns, figures, objects or people is a property of neural networks.
Fr. CRICK and Ch. KOCH give the following example and explain it: “If you look at a person whose back is turned to you, you can see the back of the head, but not the face. Nevertheless your brain infers that the person has a face. We can deduce as much because, if that person turned around and had no face, you would be very surprised.
- “The viewer-centered representation that corresponds to the visible back of the head is what your are vividly aware of. What your brain infers about the front would come from some kind of three dimensional representation” (1992, p.112).
Of course, such three-dimensional representation is present in our cerebral network as a very basic feature, acquired during the infancy. It seems moreover that there is more to it than this: We also should be very surprised if that person whould have a cat's or dog's face, which implies that we have a somehow permanent category of “human beings” in our neural network.
Moreover, the nature of our internal and potential representations obviousluy depend of our cultural training:.We easily recognize the symbols of our culture (say: the Cross, the Crescent, the Mandala, our flag, etc…), but do not recognize at all or easily symbols of other cultures.