ML Models Reference Sheet

1 · Jonathan Ramkissoon · Sept. 29, 2020, 2:22 a.m.
Resources https://maria-antoniak.github.io/2018/11/19/data-science-crash-course.html Models Linear Regression, Logistic Regression and GLM’s http://cs229.stanford.edu/notes/cs229-notes1.pdf Decision Trees and Random Forests Decision trees split the input space into non-linear regions by minimizing cross-entropy loss between regions. Let $p_c$ be the proportion of samples in region $R$ that are in class $c$, then: \[L_{cross}(R) = - \sum_c \hat{p}_c \text{log}(\hat{p}_c)\] Since cross-entrop...