The Bongard Problems • Hacker News Board

Re: The Bongard Problems

#11

Post by taneq » Sun, Jul 10, 2016, 8:35 AM UTC

thaumasiotes wrote: post #10

taneq wrote: post #9

Earlier quoted context omitted.

That's my issue with this kind of problem. There are usually a bunch of viable solutions with little if anything to differentiate them. They're not tests of intelligence so much as tests of how similar your pattern matching is to that of the test authors.

> They're not tests of intelligence so much as tests of how similar your pattern matching is to that of the test authors. Well... they are tests of intelligence. A valid test of intelligence is one that lets you determine ("predict") the intelligence of a testee from their answers. For that, you need intelligent and unintelligent people to have measurably different answer patterns, but there is no requirement that th…

But how do you select 'intelligent' people to generate your 'intelligent' answers? If it's not at some point tied back to some kind of objective performance (generating correct answers) then you're not measuring intelligence.

Re: The Bongard Problems

#12

Post by thaumasiotes » Sun, Jul 10, 2016, 9:01 AM UTC

taneq wrote: post #11

thaumasiotes wrote: post #10

Earlier quoted context omitted.

> They're not tests of intelligence so much as tests of how similar your pattern matching is to that of the test authors. Well... they are tests of intelligence. A valid test of intelligence is one that lets you determine ("predict") the intelligence of a testee from their answers. For that, you need intelligent and unintelligent people to have measurably different answer patterns, but there is no requirement that th…

But how do you select 'intelligent' people to generate your 'intelligent' answers? If it's not at some point tied back to some kind of objective performance (generating correct answers) then you're not measuring intelligence.

That's wrong. If your subjective test agrees in result with your objective test, they're measuring the same thing. That we can't begin the study of intelligence tests with a fully subjective test wouldn't mean we can't end there (and in fact, we can begin that way, because we start off with the idea that someone is smart if other people are inclined to describe them that way, not that someone is smart if they do well on a math test).

Re: The Bongard Problems

#13

Post by jldugger » Sun, Jul 10, 2016, 10:17 AM UTC

fernly wrote: post #3

Boy does this make me feel stupid. Pattern puzzles in IQ tests are always the hardest for me. The first, "trivial" example stumped me...

Technically, the "first" Bongard problem is much simpler: http://www.foundalis.com/res/bps/bongard/p001.htm

Since this was hard to find, here's the full index: http://www.foundalis.com/res/bps/bpidx.htm

Re: The Bongard Problems

#14

Post by jldugger » Sun, Jul 10, 2016, 10:20 AM UTC

taneq wrote: post #11

thaumasiotes wrote: post #10

Earlier quoted context omitted.

> They're not tests of intelligence so much as tests of how similar your pattern matching is to that of the test authors. Well... they are tests of intelligence. A valid test of intelligence is one that lets you determine ("predict") the intelligence of a testee from their answers. For that, you need intelligent and unintelligent people to have measurably different answer patterns, but there is no requirement that th…

But how do you select 'intelligent' people to generate your 'intelligent' answers? If it's not at some point tied back to some kind of objective performance (generating correct answers) then you're not measuring intelligence.

These are not intelligence tests, they're cognition tests. The goal is not to seek the correct answer, but a correct answer.

Re: The Bongard Problems

#15

Post by aaronharnly » Sun, Jul 10, 2016, 11:59 PM UTC

fernly wrote: post #3

Boy does this make me feel stupid. Pattern puzzles in IQ tests are always the hardest for me. The first, "trivial" example stumped me...

It's easier than you think -- the problem is to find a characteristic or rule that all of the lefthand objects conform to, and that all of the righthand objects do not.

The problem is not (as is sometimes the case for similar-looking IQ test problems) to find a rule that transforms the left side of each pair into the right side, or that generates the whole sequence of six iteratively. That might have been what you were searching for; I tried to do so in vain before reassessing the problem!

Re: The Bongard Problems

#16

Post by thaumasiotes » Mon, Jul 11, 2016, 1:08 AM UTC

jldugger wrote: post #14

taneq wrote: post #11

Earlier quoted context omitted.

But how do you select 'intelligent' people to generate your 'intelligent' answers? If it's not at some point tied back to some kind of objective performance (generating correct answers) then you're not measuring intelligence.

These are not intelligence tests, they're cognition tests. The goal is not to seek the correct answer, but a correct answer.

Seeking a correct answer is trivially easy, though; you can always find the rule "any of the six shapes on the left", just as you can always fit a function to any arbitrary sequence.

Re: The Bongard Problems

#17

Post by jldugger » Mon, Jul 11, 2016, 4:50 AM UTC

thaumasiotes wrote: post #16

jldugger wrote: post #14

Earlier quoted context omitted.

These are not intelligence tests, they're cognition tests. The goal is not to seek the correct answer, but a correct answer.

Seeking a correct answer is trivially easy, though; you can always find the rule "any of the six shapes on the left", just as you can always fit a function to any arbitrary sequence.

Right, but the context is that these problems comprise an evaluation suite for artificial intelligences. Even simply textually describing the shapes on the left and the right, is an accomplishment.

A better test suite would likely provide an oracle capable of generating new images belonging to the left or right and asking the program to judge which side it belongs to.