CS 451 Quiz 15
The maximum value of the Gaussian kernel is 1
Which Gaussian kernel has a narrower ("sharper") peak?
sigma^2 = 0.5
sigma^2 = 5
It is important to perform feature normalization before using the Gaussian kernel
For SVMs employing kernels, how are the "landmarks" chosen?
Some of the training data points
All of the training data points
Some of the cross validation data points
All of the cross validation data points
A SVM with a linear kernel is the same as an SVM with no kernel
An SVM with a linear kernel is very similar to
a 3-layer neural net
What is a good "regime" for SVMs with Gaussian kernels (where N = number of features and M = number of training examples)?
M small, N very large
N small, M very large
N small, M is intermediate
Gaussian kernels measure the ________ between feature x and landmark l(i)
distance / dissimilarity
proximity / similarity
If you want to use the one-vs-all approach with SVMs for multi-class classification with K classes, how many different SVMs do you need to train?
I'd enjoy a free point on this quiz
I'd like to clarify / learn more about
What kernels are
What kernels are good for
How SVMs work
What "support vector" means
What "linearly separable" means
How SVMs deal with data that are not linearly separable
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google.
Terms of Service