Selected courses in mathematics, statistics and data science I found particularly useful and well-structured are indicated in the table below. With a few exceptions, only semester courses (or equivalent workload) are indicated.
Course |
Type |
Content summary |
|---|---|---|
| Multivariate statistics | Semester course 401-3626-00, ETH Zürich |
Classical and modern methods for multivariate statistical analysis (e.g. PCA, MDS, factor analysis, cluster analysis, graphical models) |
| Linear algebra | Semester course 626-0011-00, ETH Zürich |
Theory and applications of linear algebra and linear programming with applications to systems biology |
| Probabilistic artificial intelligence | Semester course 263-5210-00, ETH Zürich |
Core modeling techniques and algorithms from statistics, optimization, planning and control (incl. Bayesian networks, probabilistic planning and reinforcement learning) with applications |
| Markov chains: mixing times and applications | Semester course 401-3614-12, ETH Zürich |
Discrete-time Markov Chains, basic properties of Markov Chains, mixing times, Markov Chain Monte Carlo (MCMC) methods and other sampling methods |
| Multilinear algebra and applications | Semester course 401-0164-00, ETH Zürich |
Multilinear forms, inner products, tensors, applications |
| Bayesian statistics | Coursera certificate |
Bayesian inference and models for discrete and continuous data |
| Machine learning | Coursera certificate |
Foundations of supervised and unsupervised learning |
| Statistical learning | EdX certificate |
Regression and classification methods, regularization, cross-validation and model selection, nonlinear models, random forests, boosting, SVM, unsupervised learning |
| Deep learning | Neural networks and deep learning, training algorithms and optimization, convolutional neural networks and sequence models |
|
| Applied data science with Python | Machine learning, plotting and data visualization, text analysis, social network analysis using python toolkits (e.g. pandas, matplotlib, scikit-learn, nltk, networkx) |
|
| Discrete mathematics | Coursera certificate |
Combinatorics, discrete probability, graphs and social networks |
| SQL for data science | Coursera certificate |
Fundamentals of SQL (with a focus on SQLite) |
| Introduction to programming with Python and Java | Code design, code testing, code debugging, object-oriented programming, inheritance and data structures in Java |
In addition, between 2018 and 2019 I completed 47 courses on DataCamp on topics such as data engineering, python programming, data wrangling, data visualization, machine learning, reproducibility and reporting. I also completed the Statistician with R track (14 courses). However, I dropped DataCamp after the company showed an inadequate response to an internal harassment incident.