Scenarios and Courses

This site contains a list of scenarios and courses.

The project website provides statically rendered HTML sites to preview the eductional materials. In order to interact with notebooks and to run code, clone the educational-materials Git repository to your own computer (see How to use deep.TEACHING Notebooks for detailed instructions).

Scenarios

A scenario is a real-world example. To solve the tasks in a scenario you might need to combine different machine learning techniques and and most likely also use different libraries. Current scenarios are:

• Medical Image Classification
• Robotic Autonomous Driving
• Natural Language Processing

Courses

This section contains a list of courses. A course is defined as a set of notebooks, which have something in common, e.g:

• The notebooks in a course follow a didactic path. E.g. the course Introduction to Machine Learning aims to teach the fundamental core concepts of neural networks. It starts with python- and numpy-basics in order to teach univariate linear regression, evolves to multivariate linear regression and then classification via logistic regression.
• The notebooks in one course might be about a certain algorithm (e.g. logistic regression) and how to implement it using different libraries (e.g. numpy, tensorflow, pytorch, pymc).

Current courses are:

• Introduction to Machine Learning
• Introduction to Neural Networks
• Convolutional Neural Networks
• Bayesian Learning
• Sequence Learning
• Differentiable Programming
• Reinforcement Learning

Prerequisites

Topics listed here are a usefull preparation to tackle the course and scenario notebooks given above.

• Scientific NumPy