Foundations for Machine Learning

This course provides a practical and theoretical tour of the most essential probability distributions that are most often used for modern machine learning and data science. We will explore the fundamental building blocks for modeling discrete events (Bernoulli, binomial, multinomial distributions) and continuous quantities (Gaussian distribution) and discuss the implications of Bayes Theorem. Moreover, we will discuss two perspectives in estimating the model parameters, namely Bayesian perspective and frequentist perspective and learn how to reason about uncertainty in model parameters themselves using the powerful beta and Dirichlet distributions for Bayesian perspective and maximum likelihood estimate for frequentist perspective. By the end of this course, you will have a fluent command of the mathematical "language" needed to understand, build, and interpret probabilistic models

• Model data with key probability distributions
• Apply Bayes theorem and maximum likelihood estimation
• Analyze uncertainty in model parameters
• Compare Bayesian and frequentist estimation approaches

• Basic familiarity with terminology
• Readiness for applied exercises