Question: SVMs solve a classification problem by, in effect, transforming the feature space into another typically higher dimensional, sometimes infinitely dimensional space and then finding a

SVMs solve a classification problem by, in effect, transforming the feature space into another typically higher dimensional, sometimes infinitely dimensional space and then finding a (possibly soft) wide margin linear separation in that other space. What is the VC-dimension of linear classifications in an infinitely dimensional space? Is that a problem? If so, does the use of wide margin separations address that problem? Explain.

Step by Step Solution

There are 3 Steps involved in it

1 Expert Approved Answer
Step: 1 Unlock blur-text-image
Question Has Been Solved by an Expert!

Get step-by-step solutions from verified subject matter experts

Step: 2 Unlock
Step: 3 Unlock

Students Have Also Explored These Related Nonparametric Statistical Inference Questions!