This problem explores the properties of the Expectation Maximization (EM) algorithm, which is often used for unsupervised learning. The EM algorithm can be analyzed in contrast to the k-means clustering algorithm, which you explored on the last problem set. In this problem, we'll be exploring the same dataset consisting of cats, dogs, and mops. An example observation from each type of object is presented below: We assume each point can be represented as a pair of (x, y) coordinates, i.e., each object is represented in two-dimensional space. Part A (1.5 points) What are the three main differences between the k-means algorithm and the general clustering version of the EM algorithm? Please state the differences using a numbered or bulleted list. This problem explores the properties of the Expectation Maximization (EM) algorithm, which is often used for unsupervised learning. The EM algorithm can be analyzed in contrast to the k-means clustering algorithm, which you explored on the last problem set. In this problem, we'll be exploring the same dataset consisting of cats, dogs, and mops. An example observation from each type of object is presented below: We assume each point can be represented as a pair of (x, y) coordinates, i.e., each object is represented in two-dimensional space. Part A (1.5 points) What are the three main differences between the k-means algorithm and the general clustering version of the EM algorithm? Please state the differences using a numbered or bulleted list