Quote:
Originally Posted by ntvy95
I'm not sure if this is the point you are talking about : Here is my understanding:
If the perceptron hypothesis set can shatter the data set then: If for every that then there exists such a that satisfies for every that . In other words, we first have for every that , then we must be able to find a that satisfies the equation if the perceptron hypothesis set can shatter the data set.

You've built up the intuition for the proof. I knew this, but when I read what you wrote, I started to have less doubt. Thanks for that. I still have some doubt, but it's even hard to describe. It's high time to move on.