Lecture 14 Quiz
what feature space does an RBF kernel transform into?
A full degree d polynomial
An infinite dimensional feature space
A 4-dimensional representation of a 3-dimensional input space
An (N+1) dimensional representation of an N dimensional input
What is a downside to using Kernels?
The number of parameters increases with the size of the training set
They are difficult to implement
They cannot represent high dimensional feature spaces
None of the above
Which training set should we tune our hyperparameters?
Never submit passwords through Google Forms.
This form was created inside of Carnegie Mellon University.
Terms of Service