We continue our discussion on Statistical Learning with a brief overview of one concept in statistics of primary importance (especially in the new age of ‘Big Data’). We start by reminding ourselves about the two statistical estimation methods we introduced last week. As with all our posts, we try and strike the difficult balance between brevity and comprehensive discussion of the topics.
Supervised Learning is the task of inferring a function from labeled training data. In particular, we observe pairs where is a set of covariates, and is a corresponding label. Our goal is to use the data to infer a function from the covariate space to the response space, typically .
I chose the following topics to be the starting point for the ‘Classes’ section of this blog.
Hello. This blog is my outlet for both random and deterministic functions of the statistics and computer science research that I see on a daily basis as a graduate student.