Hey, U.S. Open, What's a "Cognitive Highlight?"

[bottle]

Are you sure that's not gobbledygook?

Or are you saying that some video you are presenting has the power to wake us all up and see the world more clearly?

Most likely you are simply out to deride all human cognitive functions? I'm asking, not criticizing, because I don't understand.

[bottle]

It's not very clear, is it? Does it mean that the person choosing the video had a brainstorm in deciding that it was the best? Could it mean that there was one point in the match being shown where one or the other player really used their noggin? Or didn't use their noggin and therefore lost the point? Do you think, reader, that one is wrong to want more clarity?

[klacr]

The Cognitive highlight is from the IBM computer Watson
Watson is watching video from seven courts. It’s watching and listening for three things: it’s listening to the crowd noise, it’s watching player gestures and it’s following the match specifics so it knows when there’s a pressure point.

All this gets combined into a number, ranking each clip. Higher numbers indicate the more exciting clips to watch. Called Cognitive Highlights, USTA’s social media team uses this technology to serve up shareable content.

Kyle LaCroix USPTA
Boca Raton

[bottle]

The Cognitive highlight is from the IBM computer Watson
Watson is watching video from seven courts. It’s watching and listening for three things: it’s listening to the crowd noise, it’s watching player gestures and it’s following the match specifics so it knows when there’s a pressure point.

All this gets combined into a number, ranking each clip. Higher numbers indicate the more exciting clips to watch. Called Cognitive Highlights, USTA’s social media team uses this technology to serve up shareable content.

Kyle LaCroix USPTA
Boca Raton

Got it. Thanks.

[faultsnaces]

IBM should (urgently) drop the "Keys to the match" nonsense. Looking at the success and fail rates of those by set, they have worse than zero predictive power: it's not infrequent that the player who succeeds in achieving more of their "keys" in a given set than their opponent does loses the set. And, of course, the long standing issue with the "Keys" - that they are not actionable - still remains.

This sort of machine learning nonsense gives statistical analysis and IBM's Watson system a bad impression.....

-f

[bottle]

IBM should (urgently) drop the "Keys to the match" nonsense. Looking at the success and fail rates of those by set, they have worse than zero predictive power: it's not infrequent that the player who succeeds in achieving more of their "keys" in a given set than their opponent does loses the set. And, of course, the long standing issue with the "Keys" - that they are not actionable - still remains.

This sort of machine learning nonsense gives statistical analysis and IBM's Watson system a bad impression.....

-f

I wasn't quite sure why I started this thread. May have intuited a bit of pretense. And anyone who uses the phrase "machine learning nonsense," as you just did, has sunk their hooks into a gigumbo subject.

In the school where I teach, McGraw-Hill Publishing has practically taken over. Half of first week orientation was devoted to their machinations. Experts flew into Detroit from Boston to conduct a "webinar" which then electronically failed, wasting teachers' precious time needed to get ready for their first classes.

In social studies, which I teach, you have to use the book McGraw-Hill sent, the one that goes with the programmed learning that will happen when one computer rolls out for every kid.

Judging from what some kids do to a new book, I hate to think what they would do to a new computer.

While there are dish racks full of slim Chromebooks within the school (I've taken one out and opened it and played with it), there couldn't possibly be one for each of my too many students.

So what is the use? Why pretend something is going to happen that isn't going to happen?