Arthur T Knackerbracket has found the following story:
Watching a sport can be a bit odd if you aren’t familiar with it. Most Americans, for example, would think a cricket match looked funny because they don’t know the rules. If you were not familiar with baseball, you might wonder why one of the coaches was waving his hands around, touching his nose, his ears, and his hat seemingly at random. Those in the know however understand that this is a secret signal to the player. The coach might be telling the player to steal a base or bunt. The other team tries to decode the signals, but if you don’t know the code that is notoriously difficult. Unless you have the machine learning phone app you can see in the video below.
[...] The code uses SDEC (Sequence-Domain Encompassed Correlations) to look for patterns in an ASCII string. We couldn’t help but think this would probably be applicable to a lot of other things where you were looking for a sequence of things.
The video has a pretty good Sunday supplement explanation of machine learning. It includes some details like hidden layers without getting bogged down too much in math or actual coding. If you haven’t dug into machine learning yet, this won’t make you an expert, but it will give you some orientation.
If you want a more detailed explanation of how machine learning works, try this one. Even the Arduino can get in on the act.
The video: http://www.youtube.com/watch?v=PmlRbfSavbI
(Score: 1) by kiffer on Friday November 29 2019, @12:26PM (1 child)
If you were not familiar with baseball, you might wonder what "steal a base or bunt" means.
I love this because it reminds me sometimes I try to explain things using things that you only know if you already understand the thing.
It's not very important for understanding the idea; that signals need to be passed between team members, in view of others, yet kept secret...
(Score: 0) by Anonymous Coward on Friday November 29 2019, @12:33PM
that's what she said!
(Score: 0) by Anonymous Coward on Friday November 29 2019, @06:02PM (1 child)
So, now the coach knows that the AI is watching the signals and correlating with subsequent play. Seems to me that all the coach needs to do is invent random signals for the times when there is no need to signal any players.
(Score: 0) by Anonymous Coward on Friday November 29 2019, @11:34PM
They already invent "random" signals when there is no call. They also add noise around the signals when there is a call including signals telling to player to ignore any valid signal they see. The video talks about this and shoes that the program can see past all of the obfuscation.
Unfortunately for the coach, they have to emded a signal in a small amount of time meaning the signal to noise ratio is naturally going to be extremely high for a machine learning algorithm. Add in that humans make very poor random number generator, it's a losing battle. They're a reason MLB has strict limitations on allowable technology in the dugout.