Boook Club "Machine Learning with R" - Clustering

Join us for our new online boookclub session discussing ‘Hands-On Machine Learning with R’ by Bradley Boehmke and Brandon Greenwell!

Monday March 27, we will talk about pt IV of the book: Clustering! From the book:

In PART III of this book we focused on methods for reducing the dimension of our feature space (p). The remaining chapters concern methods for reducing the dimension of our observation space (n); these methods are commonly referred to as clustering. K-means clustering is one of the most commonly used clustering algorithms for partitioning observations into a set of k groups (i.e. k clusters), where k is pre-specified by the analyst. k-means, like other clustering algorithms, tries to classify observations into mutually exclusive groups (or clusters), such that observations within the same cluster are as similar as possible (i.e., high intra-class similarity), whereas observations from different clusters are as dissimilar as possible (i.e., low inter-class similarity). In k-means clustering, each cluster is represented by its center (i.e, centroid) which corresponds to the mean of the observation values assigned to the cluster. The procedure used to find these clusters is similar to the k-nearest neighbor (KNN) algorithm discussed in Chapter 8; albeit, without the need to predict an average response value.

These chapters (20-22) will be presented by one of the organizers of R Ladies Den Bosch: Martine.

The attentive reader might notice that we skipped part III of the book: dimension reduction. This part contains chapter 17 Principal Components Analysis, 18 Generalised Low Rank models, and 19 Autoencoders. If you are looking for a fun little challenge and would like to present one or more of these chapters, please send us a message!