After a series of remarkable breakthroughs in the past decade, we now have machine learning models that perform at an astonishing level. Machine Learning (ML) with numerous trainable parameters (such as deep learning models) allow the development of human-like chatbots and self-driving cars, to name a few examples. This CAS programme teaches how neural networks and deep learning work, as well as other ML approaches including classical supervised, unsupervised, reinforcement and Bayesian learning.
The CAS in Machine Learning is for everyone wishing to develop a deeper understanding of machine learning and to improve their skills in using it. Intermediate-level programming skills are welcome but not expected; you will learn Python during the course. To support participants without extensive programming experience, the first module is dedicated to brushing up coding skills with Python. If you have any questions concerning the admission requirements, please contact the head of program.
The course objective is to enable you to directly use ML systems in your day-to-day work environment. You will gain a valuable and sought-after qualification.
Module overview
Module 1 - Introduction
- Math refresher: Linear algebra, calculus, statistics
- Coding refresher: Python, Numpy, Matplotlib
- The history and development of machine learning
- Data management and feature engineering
Module 2 - Machine Learning
- Unsupervised learning
- Supervised learning
- Artificial neural networks
- Model validation
- Model diagnostics
Module 3 – Deep Learning
- Convolutional neural networks
- Computer vision
- Generative models
- Artificial neural networks
- Natural language processing (NLP)
- Transformers: All you need is attention
Modul 4 – Other types of Machine Learning
- Recommender systems
- Decision trees, random forest and gradient boosting
- Bayesian learning and Bayesian networks
- Self-supervised learning
- Reinforcement learning
Module 5 – Production deployment and MLops
- The workflow of machine learning
- Model deployment in production
- MLops concepts and strategies
- Architectures of deployment: Edge, Cloud, Browser
- Monitoring of production models
The focus lies on practical work: each topic will be explored through Python programming and group-exercise units. Guest lecturers will come in to discuss advanced topics. To qualify for a CAS certificate, participants must attend 80% of all course-related events.
Transfer project
In the transfer project, participants work with a real-life dataset. The process comprises the following stages:
- The participants either choose an existing project/problem from their professional practice or define one based on their personal interests.
- They discuss the idea with their lecturers, who directly approve it or suggest changes.
- During the program, the participants are given the time to work their project supervised by their lecturers.
- The participants present their projects on the final day of the CAS program.
The goal is for participants to gain experience with a real-life project, boosting their CV while creating added value for and their companies.
Technologies used:
- Python, Jupyter, Scikit Learn, Pandas, Numpy, Matplotlib
- Tensorflow, Keras
- GPUS and hardware acceleration