Quote:
Originally Posted by Peter_Spaeth
OK. As I am sure you know a lot of guys have touted it as the solution to all the problems brought out by the scandal, and it seems PSA new ownership has faith in it as well, although perhaps for different purposes. There have been a number of does too does not discussions here but I don't think we've had much contribution from people who really understand the technology. Maybe I missed them.
|
You missed it even in this thread. The short answer is:
There could be a whole sea of issues. I think of three questions AI/ML could help with
1) Detect if a card is real or fake
2) Classify the card (type, year, etc)
3) Classify the grade
In all of these cases, I can assure you people want to know why the algorithm gave the grade/class/ etc, e.g. explain how the algorithm got the result. This requires explainable AI, which is beyond what algorithms can do today. Furthermore, all of this requires a large training set (you need a lot of examples) including fake examples! Who has that many training examples sitting around?