Week 6

Question 1

Name the definition of set of linear classifiers.

Answer 1

Question 2

What is the definition of shattering?
What is an interpretation of it?

Answer 2

ChatGPT: Shattering is a concept in machine learning that refers to the ability of a hypothesis or a set of hypotheses to perfectly fit a given set of data points. Specifically, a set of hypotheses is said to shatter a set of data points if it can correctly classify every possible labeling of those points.

In other words, a set of hypotheses shatters a set of data points if for every possible way of assigning a label to each data point, there exists at least one hypothesis in the set that correctly classifies the data points according to those labels.

Question 3

What is the definition of shatter coefficients?

Answer 3

Question 4

What is the VC-dimention of a model?

Answer 4

Question 5

What does a VC-dimention mean?

Answer 5

Question 6

What is the set of interval classifiers?

Answer 6

Question 7

Proof the following.

Answer 7

Question 8

What is the VC-generalization bound theorem?

Answer 8

Question 9

Show a learning guarantee using linear classifiers.

Answer 9

Question 10

Proof the following.

Answer 10

Question 11

What is the VC-dimention of NN?

Answer 11

Question 12

What is the definition of shattering in a regression framework?
What is the definition of a pseudo-dimention?

Answer 12