Develop AI systems to efficiently learn new skills and solve open-ended problems, rather than depend exclusively on AI systems trained with extensive datasets
This one actually is a little trickier. The form (given by red) is consistent from input to output, but the shading rules are what we discover we need to reason about.
From the examples, we see we have cyan, yellow, or green as options. The first thing I thought to look for was to shade based on location of the form. Maybe left-most gets one color, etc. or if it was based on the relative relation between multiple forms.
After another look at all of them and seeing what commonalities each shaded color has, we realize the color is related to the area of the form we are filling.
Once we see that pattern, the puzzle is easy to complete.
Discover other posts like this one