Search: keyword:teach
|
Displaying 1-8 of 8 results found.
|
page 1
|
|
Sort:
id
Format:
long
Filter:
(all | no meta | meta)
Mode:
(words | no words)
|
|
|
|
|
BP100 |
| The letter A vs. the letter Б. |
|
| |
|
|
COMMENTS
|
This is the final problem in Bongard's original collection. It is the only member of the collection that makes reference to human culture. This can be interpreted symbolically as foreshadowing that computers will be able to perform the various tasks that humans can do.
Another idea introduced by this Bongard Problem is that a Bongard Problem can teach its solution to the solver. (See keyword teach.) A large pool of examples can be used for training, as is common in machine learning. |
|
REFERENCE
|
M. M. Bongard, Pattern Recognition, Spartan Books, 1970, p. 247. |
|
CROSSREFS
|
Adjacent-numbered pages:
BP95 BP96 BP97 BP98 BP99  *  BP101 BP102 BP103 BP104 BP105
|
|
KEYWORD
|
easy, nice, teach, arbitrary, anticomputer, culture, finished, bongard
|
|
CONCEPT
|
specific_shape (info | search), specificity (info | search)
|
|
AUTHOR
|
Mikhail M. Bongard
|
|
|
|
|
BP862 |
| Human faces vs. other images. |
|
| |
|
|
|
|
|
BP981 |
| Each column is assigned something independently; each row is assigned something independently; there is a rule that generates contents of squares from the row information and column information vs. there is a different kind of rule. |
|
| |
|
|
COMMENTS
|
To clarify the solution with an example: on the left is an image of a grid where the first row features a square with three dots and a square with nine dots, and the second row features a square with four dots and square with sixteen dots. "Three" and "four" are assigned to the rows; "x" and "x squared" are assigned to the columns.
To word the solution with mathematical jargon, "defines a (simply described) map from the Cartesian product of two sets vs. not so." Another equivalent solution is "columns (alternatively, rows) illustrate a consistent set of one-input operations." It is always possible to imagine the columns as inputs and the rows as operations and vice versa.
Left examples are a generalized version of the analogy grids seen in BP361. Any analogy a : b :: c : d shown in a 2x2 grid will fit on the left of this Problem.
All examples show grids of squares with an image in each square, such that there is some "rule" the images within the grid obey. The "rule" might be about how the images must relate to their neighbors, for example.
There is a trivial way in which any example can be interpreted so that it fits on the left side: imagine each row is assigned the list of all the squares in that row and each column is assigned its number, counting from the left. But each grid has a clear rule that is simpler than this. |
|
CROSSREFS
|
See BP979 for use of similar structures but with one square removed from the grid. Examples on the left here with any square removed should fit on the left there.
Adjacent-numbered pages:
BP976 BP977 BP978 BP979 BP980  *  BP982 BP983 BP984 BP985 BP986
|
|
KEYWORD
|
stub, convoluted, teach, structure, rules, grid, miniworlds
|
|
CONCEPT
|
analogy (info | search)
|
|
WORLD
|
grid_of_images_with_rule [smaller | same | bigger] zoom in left (grid_of_operations)
|
|
AUTHOR
|
Aaron David Fairbanks
|
|
|
|
|
BP1080 |
| Image of a Bongard Problem vs. other image. |
|
| |
|
|
| |
|
|
|
|
|
|