Advanced Machine Learning for Data Science (Spring 2022)
Official course description:
Course info
Programme
Staff
Course semester
Exam
Abstract
In this course, we teach both advanced machine learning (ML) approaches and hands-on skills for applying these approaches to data science problems.
Description
We teach the current state of the art of machine learning (ML) and applying ML to interesting data science problems. The module builds on top of the BSc course on Introductions to Machine Learning. On this basis we cover both, theoretical and computational ML learning concepts and key mechanisms, as well as technical details for programming ML approaches hands-on in leading ML frameworks.
In particular, this course covers:
- A recap on fundamental learning types, preprocessing, data repreentations and linear models,
- learning theory, and deterministic vs. probabilistic machine learning,
- supervised learning, including deep neural networks, generative & discriminative learning, and non-parametric learning such as in kernel methods
- unsupervised learning, including dimensionality reduction, clustering, and autoencoders,
- sequence learning including recurrent neural networks, and attention
- hybrid learning, including geometric learning, reinforcement learning, adaptive learning, semi-supervised learning,
- regularization, optimization.
Application areas will include data mining, bioinformatics, natural language processing, computer vision, and robotic control.
In the accompanying tutorials, we will exercise to:
- reproduce key approaches in ML frameworks such as Pytorch and Tensorflow,
- monitor and analyse training and representation of ML approaches,
- collaboratively develop & visualise ML approaches,
- develop a complete ML solution on a task of choice in a small group
Formal prerequisites
Having courses on Applied Statistics and Linear Algebra and Optimisation completed is required. A good background in basic Machine Learning and object-oriented interpreted programming languages such as Python is recommended.
Intended learning outcomes
After the course, the student should be able to:
- define and describe the state of the art approaches in machine learning (ML)
- characterise and analyse key mechanisms in major ML approaches in-depth
- implement novel ML mechanisms in leading ML frameworks and develop applications for large-scale data science problems.
Learning activities
The course will consist of lectures, accompanying exercises, and self-study material to deepen knowledge and follow personal interests with literature recommendations. In the exercises during the first ten weeks, the students will practise concepts, methods, and implementations based on prepared assignments in class. In the final four weeks, students will pair in small groups to solve a prepared mini-project of choice to practice a full machine learning cycle in a collaborative setting.
The oral examination will assess the students’ learning outcomes based on the provided material through literature and lecture as well as the practised assignments and mini-project.
Course literature
We focus mostly on the following books (available online for free) and will add specific papers during the lectures:
- Murphy, Probabilistic Machine Learning: An Introduction, MIT Press, 2022.
https://probml.github.io/pml-book/book1.html - Goodfellow, Bengio, Courville. Deep Learning, MIT Press, 2016.
https://www.deeplearningbook.org/
Student Activity Budget
Estimated distribution of learning activities for the typical student- Preparation for lectures and exercises: 20%
- Lectures: 18%
- Exercises: 24%
- Project work, supervision included: 26%
- Exam with preparation: 12%
Ordinary exam
Exam type:B: Oral exam, External (7-point scale)
Exam variation:
B22: Oral exam with no time for preparation.
30 minutes
reexam
Exam type:B: Oral exam, External (7-point scale)
Exam variation:
B22: Oral exam with no time for preparation.
30 minutes