SCREEN:
Picture of Hot and Cold Picture of Pin the Tail on the Donkey
Who knows these children’s games?
(Answers: Verbal)
Right: Hot and Cold, and Pin the Tail on the Donkey.
In Hot and Cold, you hide something in a room and as someone tries to find it, you say Hot if they get closer to it and Cold if they move farther away. We use variations to show how close or far they are: Icy cold, Freezing, Boiling hot, and so on.
In Pin the Tail on the Donkey, you first blindfold a child. Then you spin them around, put a sharp object in their hand, and let them loose in a room to find a picture of a donkey on the wall and stick it in its rear.
It’s essentially the same game, but in one case THERE ARE external guides, and in the other, the CHILD HAS to generate the hot and cold signals internally, in their mind. Shouldn’t be possible, but it is: it’s literally child’s play. So how do they do it?
OPEN TO FLOOR
They pick up on cues in the environment. They listen for the sounds of other people. They recognize things that they bump into and reorient themselves based on their position. They build a representation of the room and their place within it in their mind.
HEAVY STUFF. FORTUNATELY, IT’S A COMMON ENOUGH OCCURANCE THAT WE HUMANS HAVE COME UP WITH A WORD FOR IT: In other words, they use their imagination.
SCREEN:
IMAGINATION (fancy, sfx)
Hot and Cold is an example of what is known in AI circles as Supervised or surface learning. Pin the Tail on the Donkey is an example of Unsupervised or deep learning. What AI research has discovered, essentially, is that people can’t SOLVE PROBLEMS—THEY CAN’T really learn anything—without applying their imagination.
So the question becomes, can a computer have an imagination? Oddly enough, they can. It’s called backprop, short for backpropagation or “the backwards propagation of errors.”
SCHEMATIC OF BACK PROP
Instead of getting feedback from an outside observer, they have an internal loop in which they take what is essentially a guess, see the result, compare that to the target result, and take another guess—just like we do.
So IN THE supervised learning MODEL OF AI, WHERE YOU HAVE EXTERNAL TEACHERS TELLING YOU WHETHER YOU’RE RIGHT OR WRONG, HOT OR COLD, for instance, you MIGHT feed a computer photos of cats and photos with no cats, and label them.
PHOTO A PHOTO B
CAT NO CAT
THE PROGRAM EVENTUALLY LEARNS TO IDENTIFY WHETHER A CAT IS PRESENT IN A PHOTO OR NOT. AMAZING!
With unsupervised learning, LIKE PIN THE TAIL ON THE DONKEY, you WOULD give the computer photos OF ONLY cats, and then a bunch of mixed photos, some with cats and some without, but with no labels, and you let it apply ITS experience to sort them out.
As you can imagine, it takes a long time to get this right.
Clear. Concise. Creative.
October 14, 2020

Hi. Thanks for dropping by!
I’ve been in the Training & Development business for about 30 years, ten as a full time training and communications consultant for financial institutions and 20 freelancing for a variety of industries while also pursuing screenwriting.
I have a certificate in Courseware Design and Production and a B.Sc. in Cognitive Science. The former focused on instructional design for eLearning and the latter explored how the brain works, with a focus on how learning happens. I try and keep both in mind when designing and facilitating courses for contemporary digital audiences.
Please get in touch to discuss your specific needs. My door is always open!
I’ve been in the Training & Development business for about 30 years, ten as a full time training and communications consultant for financial institutions and 20 freelancing for a variety of industries while also pursuing screenwriting.
I have a certificate in Courseware Design and Production and a B.Sc. in Cognitive Science. The former focused on instructional design for eLearning and the latter explored how the brain works, with a focus on how learning happens. I try and keep both in mind when designing and facilitating courses for contemporary digital audiences.
Please get in touch to discuss your specific needs. My door is always open!