This course presents a comprehensive, project-based introduction to data science and artificial intelligence through four progressive modules. The curriculum begins with supervised regression, teaching learners to build predictive models from tabular health data using Pandas and Scikit-Learn. It then transitions to unsupervised learning, where students explore clustering techniques on real-world weather data for French cities, gaining experience with REST API integration, data serialization, and pipeline construction. The third module shifts to natural language processing, guiding learners through the end-to-end text classification pipeline — from raw document loading and vectorization (CountVectorizer, TF-IDF) to classifier comparison (Naive Bayes vs. SVM) using a twitter dataset. Finally, the course culminates in deep learning, where learners design and train a feedforward neural network in TensorFlow/Keras to recognize handwritten digits from the MNIST dataset, deploying the trained model through an interactive Gradio web interface. Spanning regression, clustering, text classification, and image recognition, the course provides a unified hands-on foundation across the breadth of modern machine learning.

This cookbook gives an introduction to Geospatial AI (GeoAI).

An introduction to relational databases (like SQLite and PostgreSQL) and SQL with a focus on spatial data queries.

Quantum mechanics from scratch: Implement your own numeric solvers for wavefunctions in one dimension, for the wavefunctions of a hydrogen atom, as well as simple diatomic systems with your own Hartree-Fock solver.

This TU Cookbook covers microwave remote sensing for drought monitoring. Microwave sensors penetrate soils to retrieve soil moisture data. Microwave records from EUMETSAT scatterometers (H SAF ASCAT) on Metop satellites can be used to derive long soil moisture timeseries (2007 to recent). This pr...

This course teaches you how modern artificial intelligence (AI) and machine learning (ML) methods are used to analyze, predict, and design chemical systems.

This collection of interactive Jupyter Notebooks teaches students how to evaluate and prepare network traffic data for machine learning. Through four hands-on modules, learners tackle real-world challenges like extreme sparsity, anomalies and class imbalance. Students master exploratory data anal...

This cookbook treats the city as a dataset and Vienna as the default study area. Students begin by pulling live building footprints and street networks directly from OpenStreetMap using osmnx, then graduate to the city's own open data portal (data.wien.gv.at), where hundreds of WFS endpoints deli...

A cookbook about geospatial data handling.