Left examples have the keyword "teach" on the OEBP.

Sometimes instead of gauging somebody's ability to guess the pattern, a Bongard Problem might teach the pattern.

Consider a Bongard Problem whose left examples are images of a specific person's face; after seeing that Problem, one might be able to recognize that person.

A "teach" Bongard Problem (with a huge number of examples) could be taken as a training set for machine learning.

"Teach" BPs tend to be @convoluted, @arbitrary, cultural-knowledge-based (keyword @culture), or they illustrate some insight that might be overlooked, perhaps mathematical (keyword @math).

Left examples have the keyword "teach" on the OEBP.

Sometimes instead of gauging somebody's ability to guess the pattern, a Bongard Problem might teach the pattern.

Consider a Bongard Problem whose left examples are images of a specific person's face; after seeing that Problem, one might be able to recognize that person.

A "teach" Bongard Problem (with a huge number of examples) could be taken as a training set for machine learning.

"Teach" BPs tend to be convoluted (left-BP549), arbitrary (left-BP950), cultural-knowledge-based (left-BP521), or they illustrate some insight that might be easily overlooked, perhaps mathematical (left-BP571).

Left examples have the keyword "teach" on the OEBP.

Sometimes instead of gauging somebody's ability to guess the pattern, a Bongard Problem might teach the pattern.

Consider a Bongard Problem whose left examples are images of a specific person's face; after seeing that Problem, one might be able to recognize that person.

A "teach" Bongard Problem (with a huge number of examples) could be taken as a training set for machine learning.

"Teach" BPs tend to be convoluted (left-BP549), arbitrary (left-BP950), cultural-knowledge-based (%cult%), or they illustrate some insight that might be easily overlooked, perhaps mathematical (left-BP571).

Left examples have the keyword "teach" on the OEBP.

Sometimes instead of gauging somebody's ability to guess the pattern, a Bongard Problem might teach the pattern.

Consider a Bongard Problem whose left examples are images of a specific person's face; after seeing that Problem, one might be able to recognize that person.

A "teach" Bongard Problem (with a huge number of examples) could be taken as a training set for machine learning.

"Teach" BPs tend to be convoluted (left-BP549), arbitrary (left-BP950), or they illustrate some insight that might be easily overlooked, perhaps mathematical (left-BP571).

Bongard Problems whose examples might be used to teach the rule of the solution vs. other Bongard Problems.

Left examples have the keyword "teach" on the OEBP.

Sometimes instead of gauging somebody's ability to guess the pattern, a Bongard Problem might teach the pattern.

Consider a Bongard Problem whose left examples are images of a specific person's face; after seeing that Problem, one might be able to recognize that person. Likewise such a Bongard Problem (with a huge number of examples) could be taken as a training set for machine learning.

"Teach" BPs tend to be convoluted (left-BP549), arbitrary (left-BP950), or they illustrate some insight that might be easily overlooked, perhaps mathematical (left-BP571).

Left examples have the keyword "teach" on the OEBP.

Sometimes instead of gauging somebody's ability to guess the pattern a Bongard Problem might teach someone (or a computer) to recognize the solution property.

Consider a Bongard Problem whose left examples are images of a specific person's face; after seeing that Problem, one might be able to recognize that person. Likewise such a Bongard Problem (with a huge number of examples) could be taken as a training set for machine learning.

"Teach" BPs tend to be convoluted (left-BP549), arbitrary (left-BP950), or they illustrate some insight that might be easily overlooked, perhaps mathematical (left-BP571).

Left examples have the keyword "teach" on the OEBP.

Sometimes instead of gauging somebody's ability to guess the pattern a Bongard Problem might teach someone (or a computer) to recognize the solution property.

Consider a Bongard Problem whose left examples are images of a specific person's face; after seeing that Problem, one might be able to recognize that person. Likewise such a Bongard Problem (with a huge number of examples) could be taken as a training set for machine learning.

Bongard Problems whose examples might be used to teach the pattern of the solution vs. other Bongard Problems.

Left examples have the keyword "teach" on the OEBP.

Sometimes when Bongard Problem solutions are unusually specific, they instead of gauging somebody's ability to guess the pattern might teach someone (or a computer) to recognize those specific properties together. For example, imagine a Bongard Problem whose left examples are images of a specific person's face; after solving that Problem, somebody might be able to recognize that person. The examples of such a Bongard Problem (if huge amounts are given) could be used as training for artificial intelligence programs to being able to sort based on that pattern.

Aaron David Fairbanks

Bongard Problems with "world" two shapes (as in BP792) vs. other Bongard Problems.

Aaron David Fairbanks