Julian M. Del Fiore

A training set $X$ composed of $m$ samples, i.e., $X = (x^{(1)}, \ldots, x^{(m)})$, can be modeled as the outcome of a random variable $\mathcal{X}$. If we knew how this variable behaves, we would then be able to characterize the dataset. The behavior of a random variable is determined by... [Read More]

Logistic regression is a supervised machine learning algorithm used in classification tasks where a target variable $y$ may take $K$ possible values, and we are interested in labeling an observation $\mathbf{x}$ composed of $N$ features/predictors. In particular, logistic regression is used in binary classification tasks, i.e., cases where $K=2$. However,... [Read More]

Linear and polynomial regression are supervised machine learning algorithms used, as their names indicate, to perform regression tasks, i.e., to estimate the values of a continuous response/target variable $y$. [Read More]

As human beings, we like understanding what surrounds us, either for the simple sake of knowing or because this gives us predictability. In that sense, in many situations it arrives that we have a problem that we want to model, e.g., from a phenomenon that depends only on basic physics... [Read More]

The objective is to determine to which class $\hat{y}$ an unlabelled observation $x$ belongs to, out of $K$ available. We assume that $x$ is composed of $n$ features/predictors, i.e., $x=(x_1,\ldots,x_n)$. [Read More]