Probability for Data Science

A strong understanding of probability is critical for becoming a successful data scientist. Probability is a key mathematical concept that is essential for modeling and understanding computer system performance and real-world data generated from day-to-day activities and interactions. In particular areas such as data science, machine learning, natural language processing and computer vision rely heavily on probabilistic models.

This short course in probability is designed to provide the necessary background for learning and understanding machine learning and data science concepts. Specifically, the course will introduce the concept of probability, provide an overview of discrete random variables and describe how to compute expectation and variance. The course will also discuss specific distributions such as geometric, binomial and Poisson distributions. The course includes multiple worked-out examples so that students can appreciate how to apply the concepts learnt in the lectures.

At the end of the course, students will

1. Be able to describe the basic probability concepts such as mean, variance, conditional probability, Bayes rule and statistical independence.
2. Be able to compute the mean and variance of random variables.
3. Be able to describe discrete and continuous distributions such as geometric, binomial and Poisson
4. Be able to understand how real-world phenomena can be modeled using probability distributions.