Insel-Login Aktuell gibt es Probleme beim Login mit Insel-Accounts via SWITCHaai (betrifft u.a. ILIAS, KSL). Die entsprechenden Stellen wurden informiert. Dozierende der Humanmedizin wenden sich bitte zwecks Folien-Upload an: studium.meddek@unibe.ch
Symbol Kurs

2023-01-23 - 2023-01-27 CAS ADS M6 Deep Learning (ONLY FOR CAS ADS)

Machine Learning and Deep Neural Networks with TensorFlow tutorials in the ski resort Muerren.

Reiter

CAS ADS Module 6 Deep Learning - ONLY FOR CAS ADS PARTICIPANTS
Learn machine learning in the mornings and practise your own neural network (brain) while skiing or working in the afternoons.

About
Due to increased access to data and compute capacity Machine Learning and Artificial Intelligence have become useful in many areas. In research and industry it is applied in various fields. Image recognition, online discrimination, natural language treatment, robotics, omics ... you name it.

In this winter school on machine learning you attend lectures and tutorial sessions over four mornings. This happens in Muerren, a great ski resort, in the cool old hotel Regina. You make your own ML project (expected workload 30 hours) and present it in an in-person session at the University of Bern two weeks later.

Learning outcomes, participants will
  • know basic concepts of neural networks and learning
  • can mangage basic operations in TensorFlow and know what a computational graph is
  • can solve optimization problems
  • can use neural networks in TensoFlow for digit recognition
  • can visualize learning processes and computational graphs in TensorBoard
  • can process images and signals with deep convolutional networks
  • can apply TensorFlow for machine learning on own datasets
Target group
  • CAS Applied Data Science Students
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, evening talks, tutorials (with Jupyter notebooks), project work with presentation or report
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
For CAS Applied Data Science Colleagues
  • This winter school is the Module 6 of the University of Bern Certificate of Applied Studies (CAS) Applied Data Science. 
Time : 2023-01-23 - 2023-01-27 (afternoons for work, skiing, wellness or whatever) 
Location : Legendary Regina Hotel in Muerren, 2h from Bern with public transport. Remote participation will be possible.
Fee: free of charge for CAS Applied Data Science participants.

Regarding Corona the school follows University, Cantonal and Federal measures. Short-term changes in the schedule can be possible. All sessions are in hybrid mode, i.e. onsite with online tranmission. 

Language: English
Participants : Max 24
Registration : Mandatory
Responsible : PD Dr. Sigve Haug
Monday (Arrival)
17:00 - 19:00 Hang out in the lobby
19:00 - 20:00 Dinner at Hotel Regina
 
Tuesday
08:00 - 09:00 Deep Feedforward Networks - Introduction (Radhakrishna)
09:15 - 10:15  Tutorial (Mykhailo)
10:15 - 10:45 Coffee break
10:45 - 12:30 Tutorial (Mykhailo)
12:15 - 17:00 Skiing, work or whatever
17:00 - 18:30 Tutorial (Mykhailo)
19:00 - 20:00 Dinner at hotel Regina
21:00 - 21:45 Neural Style Transformations (an example on how to use deep ML to create art)

Wednesday
08:00 - 08:45 Deep Feedforward Networks - Regularization, Optimisation (Radhakrishna)
09:00 - 10:00 Machine Ethics (Claus)
10:00 - 10:30 Coffee break
10:30 - 12:30 Tutorial (Mykhailo)
12:30 - 17:00 Skiing, work or whatever
17:00 - 18:30 Tutorial (Mykhailo) 
19:00 - 20:00 Dinner at hotel Regina
21:00 - 21:45 Facebook's Mixup Approach for Deep Learning (evening lecture by Radhakrishna)

Thursday
08:00 - 08:45 Lecture (Radhakrishna)
09:00 - 10:00 Tutorial (Mykhailo)
10:00 - 10:30 Coffee break
10:30 - 12:30 Tutorial (Mykhailo) 
17:00 - 18:00 Project discussions (Mykhailo, Sigve)
19:00 - 20:00 Cheese Fondue at Restaurant Allmendhubel (train departure at 18:30)
21:00 - 21:30 Sledge ride down to Murren

Friday
08:00 - 08:45 Lecture (Radhakrishna)
09:00 - 10:00 Tutorial (Mykhailo)
10:00 - 10:30 Coffee break and Check Out
10:30 - 11:15 Tutorial / Discussion Session (Mykhailo)
11:15 - 12:00 Wrap up (Sigve) 
12:00             End of school
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 (max 10 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 - TBD

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://archive.ics.uci.edu/ml/index.php
https://www.kaggle.com/datasets
Registration: Here on Ilias
You are free to bring familiy and friends of course (not participating in the school). Any additional arrangements with the hotel regarding this, you have to organize yourself.  
 
Arrival:            Monday, 23. of January 2023 (evening dinner at 19:00). School starts Tuesday morning at 08:00. (With the 06:04 train on Tuesday you can make the Tuesday morning if you don't want to arrive on Monday)
Depature:       Friday, 27. of January 2023 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 Stechelberg.      

Leasure:          Muerren offers spa, outstanding skiing slopes, swimming pool etc. Inform yourself:  muerren.swiss/en/winter/
  • You will profit a lot more from the school if you read a bit up front in these online resources (google it)The lecture is largely based on this book: https://www.deeplearningbook.org/
Further resources:
Pattern Recognition and Machine Learning by Christopher M. Bishop.
Machine Learning: a Probabilistic Perspective  by Kevin P. Murphy.
Varoius courses on Coursera.org etc : Machine Learning @ Stanford (Andrew Ng)
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 working for the Albert Einstein Center for fundamental Physics and the Mathematical Institute of the University of Bern where is leading the Science IT Support unit. Beyond science he likes philosophical conversations in the evening, Telemark skiing and friendly people. 

Dr. Rahdakrishna Achanta, Swiss Data Science Center (lectures)

No comments.

Dr. Mykhailo Vladymyrov (tutorials)

Mykhailo is a trained physicist from the Albert Einstein Institute of Fundamental physics with many years of experience with big data, machine learning and GPU computing. He is now working for the Theodor Kocher Institute and the Mathematical Institute. Mykhailo has a high level humor and view upon the human strive. You will enjoy his tutorials.

Lecturers from previous years:

Simon Jenni, University of Bern
Prof. Dr. Paolo Favaro, University of Bern
Dr. Fernando Perez-Cruz, Swiss Data Science Center
Dr. Qiyang Hu, Computer Science, University of Bern

Dr. Geraldine Conti (lectures)

Geraldine has a PhD from EPFL, has been a research associate at Harvard, a CERN fellow, a research associate at Disney Research, associated professor in machine learning and is now head of the machine learning group at PAG.
Her skiing skills are still unknown.

Prof. Dr. Dr. Claus Beisbart

Claus is our school philosopher and helps with the bigger picture and ethical aspects. http://www.philosophie.unibe.ch/ueber_uns/personen/beisbart/index_ger.html

More to come