2023-01-17 - 2023-01-20 Machine Learning for Time Series
For CAS AML participants as elective module 6
Tabs
About
- Machine Learning with Time Series (TS)
About
In this module we study and practise techniques for doing forecasting, i.e. machine learning on time series.
Possible learning objectives
- TS data - univariate and multivariate
- TS with classical / statistical methods
- TS with classical machine learning methods
- TS with RNN (deep learning)
- TS with LSTM (deep learning)
- TS witth CNN (deep learning)
- TS with Transformers (deep learning)
- TS with ...
Target groug
CAS AML, UNIBE staff, students and externals
Prerequisites- You must bring your own laptop
- Mathematics and statistics at the level of an introductionary course on university level
- Python knowledge and programming experience
- Experience with machine learning and in particular with neural networks
Methods - Talks, tutorials (with Jupyter notebooks on colab), project work with presentation
Certificate - A certificate will be delivered to participants who have attended the whole training and presented their project work successfully. The school yields 2 ECTS points.
Coaches - The coaches are local and external experts
- Readings
Forecasting: Principles and Practice - https://otexts.com/fpp2/
Practical information (time, location ...)
Time : 2023-01-17 - 2023-01-20
Location : HG 117 (Tue, Wed, Thu), HG 104 (Fri)
URL: Zoom Link will appear here
Language: English
Participants : Max 20
Registration : Mandatory
Responsible : PD Dr. Sigve Haug
Location : HG 117 (Tue, Wed, Thu), HG 104 (Fri)
URL: Zoom Link will appear here
Language: English
Participants : Max 20
Registration : Mandatory
Responsible : PD Dr. Sigve Haug
Schedule
Lectures require voluntary lecturers, if not found they become tutorials
Tentative Schedule
Tuesday
09:00 - 09:45 Introduction to Time Series (TS) - Lecture 1
10:00 - 10:30 Tutorial 1 TS with TF
10:30 - 11:00 Break
11:00 - 11:15 Discussion
11:15 - 12:15 Tutorial 1 TS with TF
12:15 - 12:30 Discussion
Wednesday
09:00 - 09:45 Traditional TS Models - Lecture 2
10:00 - 10:30 Tutorial
10:30 - 11:00 Break
11:00 - 12:30 Tutorial
Thursday
09:00 - 09:45 TS with Deep Learning - Lecture 3
10:00 - 10:30 Tutorial
10:30 - 11:00 Break
11:00 - 12:30 Tutorial
Friday
09:00 - 09:45 TS with Transformers - Lecture 4
10:00 - 10:30 Tutorial
10:30 - 11:00 Break
11:00 - 11:30 Tutorial / discussion session
Presentation day to be defined during module.
Tentative Schedule
Tuesday
09:00 - 09:45 Introduction to Time Series (TS) - Lecture 1
10:00 - 10:30 Tutorial 1 TS with TF
10:30 - 11:00 Break
11:00 - 11:15 Discussion
11:15 - 12:15 Tutorial 1 TS with TF
12:15 - 12:30 Discussion
Wednesday
09:00 - 09:45 Traditional TS Models - Lecture 2
10:00 - 10:30 Tutorial
10:30 - 11:00 Break
11:00 - 12:30 Tutorial
Thursday
09:00 - 09:45 TS with Deep Learning - Lecture 3
10:00 - 10:30 Tutorial
10:30 - 11:00 Break
11:00 - 12:30 Tutorial
Friday
09:00 - 09:45 TS with Transformers - Lecture 4
10:00 - 10:30 Tutorial
10:30 - 11:00 Break
11:00 - 11:30 Tutorial / discussion session
Presentation day to be defined during module.
Project Instructions
For the 2 ECTS certificate you need to do a project:
Goal: Apply what has been learned in the tutorials to a similar or different task (T) on own or public data (E) and ideally assess the performance (P) of the task solving.
Expected effort: 30 hours
Result: 15 minutes presentation (your notebook optionally with some slides) to be uploaded to Ilias together with the Jupyter notebook or Python script used (Naming convention: surname_1-surname_2-projectname.pdf/ipynb)
Teamwork: Please work and present in teams of two (or three). Exceptionally you can work alone.
Slots for presentations will be agreed upon during the course week.
Assessment: You will get feedback (15 minutes) right after your presentation. If you have given it a good try (~30h) your project will pass. There is no further grading. The project together with school attendance yield 2 ECTS credit points.
Goal: Apply what has been learned in the tutorials to a similar or different task (T) on own or public data (E) and ideally assess the performance (P) of the task solving.
Expected effort: 30 hours
Result: 15 minutes presentation (your notebook optionally with some slides) to be uploaded to Ilias together with the Jupyter notebook or Python script used (Naming convention: surname_1-surname_2-projectname.pdf/ipynb)
Teamwork: Please work and present in teams of two (or three). Exceptionally you can work alone.
Slots for presentations will be agreed upon during the course week.
Assessment: You will get feedback (15 minutes) right after your presentation. If you have given it a good try (~30h) your project will pass. There is no further grading. The project together with school attendance yield 2 ECTS credit points.
Lecturers and Coaches
PD Dr. Sigve Haug
Sigve studied physics in Germany, Spain and Norway. He has been involved in neutrino physics experiments and high energy frontier experiments, often with main focus on the computing challenges related to the large and distributed data from these experiments. Today he is heading the Data Science Lab of the University of Bern.
Sigve studied physics in Germany, Spain and Norway. He has been involved in neutrino physics experiments and high energy frontier experiments, often with main focus on the computing challenges related to the large and distributed data from these experiments. Today he is heading the Data Science Lab of the University of Bern.