I started watching ML videos of Andrew Ng on Coursera. In the lesson on Classification (in the third video), he said the following lines
"Once again, the decision boundary is a property not of the training set, but of the hypothesis and of the parameters.
But once you have the parameters theta, that is what defines the decision boundary."
My questions:
What is the difference between the training set and hypothesis?
Why is the decision boundary a property of hypothesis and not of training set?