2027-03-01 - 2027-03-05 Bern Winter School - Deep Learning
Reiter
Introduction to Modern Maching Learning
About
This Winter School provides a practical introduction to the foundations and applications of modern machine learning. Designed for participants who want to build a solid understanding of today's ML landscape, the program combines core concepts with hands-on experience using state-of-the-art tools and frameworks.
In this winter school you attend lectures and tutorial sessions over four mornings. This happens in Muerren, a great ski resort, in the grand old hotel Regina. You may make your own ML project (expected workload 30 hours) and present it in an in-person session at the University of Bern or online some weeks later. The project is voluntary, however, needed for those aiming for the ECTS points
By the end of this winter school, participants will be able to:
- Know what ML is
- Solve optimization problems
- Know how to select a most promising approach and quantify model generalization
- Have an overview of modern machine learning methods from traditional methods to SOTA deep models.
- Implement a basic neural network or adapt existing model architecture.
- Know how to apply AI assistance in development and project maintenance.
- Critique a machine learning approach.
Target group
- PhD students, postdoctoral researchers, UniBE starr and external participants seeking to strengthen their expertise in modern machine learning.
Prerequisites
- You must bring your own laptop
- Mathematics and statistics at the level of an introductionary course on university level
- Basic Python knowledge
- The training is as language independent as possible, but examples and practical work is in Python
Methods
- Theoretical lectures, tutorials (with Jupyter notebooks), project work with presentation or report (can be skipped if you don't want the ECTS points, but own work and presentation increase your skills dramatically)
Certificate
- A certificate of attendance will be delivered to participants who have attended the whole training. A certificate with 2 ETCS points will be delivered to particiants who have performed and presented a project work
Coaches
- The coaches are local and external experts
Time : 2027-03-01 - 2027-03-05 (afternoons for work, skiing, wellness or whatever)
Location : Legendary Regina Hotel in Muerren, 2h from Bern with public transport: https://www.reginamuerren.ch/
Check-In: Your room is ready for occupancy from 3 pm on the day of arrival.
Check-Out: On the day of departure, you are asked to vacate the room by 10 am and hand in the key at the reception
Fee students and UniBE staff: 660 CHF (fee) + about 900 CHF (accommodation costs including private room with shared bathroom, breakfast, coffee break, lunch bag, dinner and social program).
Fee others: 1160 CHF (fee) + about 900 CHF (accommodation costs including private room with shared bathroom, breakfast, coffee break, lunch bag, dinner and social program).
Language: English
Participants : Max 20
Registration : Mandatory
Responsible : PD Dr. Sigve Haug
Monday (Arrival)
14:00 - 14:15 Welcome (Sigve)
14:15 - 15:00 Machine Learning Introduction and Tutorial (Sigve)
15:15 - 17:00 Machine Learning Introduction and Tutorial (Sigve)
17:30 - 18:30 Apéro
19:00 - 20:30 Dinner (Regina)
Tuesday (Matthew)
08:15 - 09:00 Lecture 1
09:00 - 10:00 Tutorial
10:00 - 10:30 Coffee break
10:30 - 12:30 Tutorial
12:30 - 17:00 Skiing, work or whatever (lunchbags in the hotel bar)
17:00 - 18:30 Tutorial
19:00 - 20:00 Dinner (Regina)
Wednesday (Matthew and Mykhailo)
08:15 - 09:00 Lecture 2
09:00 - 10:00 Tutorial
10:00 - 10:30 Coffee break
10:30 - 12:30 Tutorial
12:30 - 17:00 Skiing, work or whatever (lunchbags in the hotel bar)
17:00 - 18:30 Tutorial
19:00 - 20:00 Dinner (Regina)
20:30 - 21:39 Mirren DL Quiz in the Bar
Thursday (Mykhailo)
08:15 - 09:00 Lecture 3
09:00 - 10:00 Tutorial
10:00 - 10:30 Coffee break
10:30 - 12:30 Tutorial
12:30 - 15:00 Skiing, work or whatever, lunchbags in the hotel bar
15:00 - 16:30 Project discussions, if any, and more tutorial
16:45 - 18:00 Sledge ride, we leave the Regina reception at 16:45
19:00 - 21:00 Cheese Fondue at hotel Alpenruh, meet at Regina reception at 18:45
21:30 - 0X:XX Tächibar
Friday (Mykhailo)
08:15 - 09:00 Lecture 4
09:00 - 10:15 Tutorial
10:00 - 10:30 Coffee break and check out
10:30 - 12:15 Tutorial / discussion session
12:15 - 12:30 Wrap up
12:30 End of school (lunchbags in the hotel bar)
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.
Presentations:
16.04.2027: 9:30 - 12:30 (Cancelled - no subscriptions)
17.04.2027: 9:30 - 12:30
Room: Main Building, room 204
Zoom: https://unibe-ch.zoom.us/j/63463506396?pwd=oyL6gTRJRH67NOutykw6Dds13banoZ.1
Please book a slot here: https://nuudel.digitalcourage.de/C1wLUsdBiTCPfDTQ.
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.
Links with public datasets you may use (you better choose something easy, i.e. well formatted):
https://huggingface.co/datasets
https://www.kaggle.com/datasets
https://en.wikipedia.org/wiki/List_of_datasets_for_machine-learning_research
https://archive.ics.uci.edu/ml/index.php
https://www.openml.org/search?type=data
Subscription for slots will be circulated shortly before the presentations.
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.
Links with public datasets you may use (you better choose something easy, i.e. well formatted):
https://huggingface.co/datasets
https://www.kaggle.com/datasets
https://en.wikipedia.org/wiki/List_of_datasets_for_machine-learning_research
https://archive.ics.uci.edu/ml/index.php
https://www.openml.org/search?type=data
Registration: If you have an ILIAS or AAI account (people affiliated with a Swiss higher education organisation), please login and join the course. For others, please write an email to info.dsl@unibe.ch.
You are free to bring familiy and friends of course (not participating in the school), if there are rooms free. Costs for additional travellers are on your own expenses.
Disclaimer: Editions with less than 10 registrations will be cancelled one month in advance.
Cancellation policy and refunds: Cancellation is possible only until three weeks before the Winter School starts. No refunds will be made for cancellation received later or for no-shows. Moreover, participants will be charged by the University of Bern for the accommodation costs at Hotel Regina.
The notice of cancellation needs to be submitted in written form to: info.dsl@unibe.ch
All refunds will be made after the Winter School is finished.
Payments in full will only be refunded if the Winter Schools must be cancelled by the organizers (except cancellations due to force majeure of any kind). The organizers will have no further liability to the client.
Arrival: Monday 01 of March 2027. School starts 14:00 and evening dinner is at 19:00.
Departure: Friday, 05 of March 2027 at noon (if you don't stay longer for your pleasure)
Travel: By public transport 2 hours from Bern (sbb.ch). Muerren is a car free village. You can park in Lauterbruennen or Stechelberg.
Mürren can be reached from the Lauterbrunnen Valley via two connections:
- From Lauterbrunnen by cable car and a mountain railroad via Grütschalp to Mürren BLM.
- From Stechelberg by cable car via Gimmelwald to Mürren Schilthornbahnen LSMS.
Lauterbrunnen is easily accessible by train from Interlaken. The route via Stechelberg is mainly preferred by motorists because of the parking spaces at the Stechelberg valley station. Stechelberg can also be reached from Lauterbrunnen by post bus.
Leasure: Muerren offers spa, outstanding skiing slopes, swimming pool etc.
Inform yourself: muerren.swiss/en/winter/
Ideally you prepare yourself with this python notebook before the school (download it and run it on colab)
- https://github.com/neworldemancer/DSF5/blob/course_2023/Python_key_points_homework.ipynb
If you need some material for solving that notebook, you can use this book:
- https://github.com/jakevdp/PythonDataScienceHandbook
A much used refrence for deep learning is this fat text book, however, it is older than the Transformers
- https://www.deeplearningbook.org/
Timeseries Tutorials:
https://github.com/sktime/sktime-tutorial-europython-2023/blob/main/notebooks/03_forecasting.ipynb
https://colab.research.google.com/drive/163hxF_dhAc0-9JL8VsXAfEiBiMyehwSj?usp=sharing#scrollTo=Kem30j8QHxyW
Dr. Mykhailo Vladymyrov (lectures and tutorials)
Mykhailo is a trained physicist who worked at the Albert Einstein Institute of Fundamental physics (and beyond) with many years of experience with big data, machine learning and GPU computing. Today he is working for the Data Science Lab at the University. Mykhailo has a high level humor and view upon the human strive. Apparantly he is capable of skiing.
Dr. Matthew Vowels (lectures and tutorials)
Matthew is CTO for a New York based precision psychiatry company Kivira Health. He also works as a senior researcher for The Sense Innovation and Research Center at the hospital CHUV, Lausanne. He has experience in computer vision, causal statistics, LLM benchmarking, and applied machine learning in human and social sciences. He does ski, however, we haven't seen it.
PD Dr. Sigve Haug (overview, school responsible)
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 coordinating the Data Science Lab at the University. Beyond science he likes philosophical conversations in the evening, snow sport, cycling, running and friendly people.