Summary

Over the course of this chapter, we gained a strong and high-level understanding of the field of UL, its uses, and its applications. We then explored a few of the most popular ML methods as they relate to clustering and DR. Within the field of clustering, we looked over some of the most commonly used models such as hierarchical clustering, K-Means clustering, and GMMs. We learned about the differences between Euclidean distances and probabilities and how they relate to model predictions. In addition, we also applied these models to the Wisconsin Breast Cancer dataset and managed to achieve relatively high accuracy in a few of them. Within the field of DR, we gained a strong understanding of the significance of the field as it relates to the COD. We then implemented a number of models such as PCA, SVD, t-SNE, and UMAP using the single-cell RNA dataset in which we managed to reduce more than 1,400 columns down to 2. We then visualized our results using seaborn and examined the...