VC Dimension Lookup

Problem

Return the VC dimension of a named hypothesis class, where d is the ambient dimension for classes that depend on it. Use these rules: interval -> 2, rectangle -> 4, halfspace -> d + 1, monotone_conjunction -> d, sinusoid -> -1 (infinite), and 0 for anything else.

Hint

A class with infinite VC dimension cannot be PAC learned without restrictions.

Test cases

case 1

in: ["interval",1]

expected: 2

case 2

in: ["rectangle",2]

expected: 4

case 3

in: ["halfspace",3]

expected: 4

case 4

in: ["sinusoid",1]

expected: -1

case 5

in: ["monotone_conjunction",5]

expected: 5

Starter codePython

def vc_dimension(name, d):
    # Your code here
    pass

5 test cases · run your code against them in the editor