2022-08-23 CAS AML M1 Machine Learning Review (4 half days)
CAS Advanced Machine Learning Module 1
Reiter
About Module Machine Learning Review
CAS Advanced Machie Learning Module 1
See study plan on math.unibe.ch/cas_aml
Learning outcomes
See study plan on math.unibe.ch/cas_aml
Learning outcomes
- know general concepts and methods of machine learning
- can design, tune, and train neural networks
- can measure performance of neural networks Learning objectives
- Learning Algorithms
- Capacity, Over- and Under-Fitting
- Hyper-Parameters and Validation Set
- Estimators, Bias and Variance
- Maximum Likelihood Estimation
- Bayesian Statistics
- Supervised Learning Algorithms
- Unsupervised Learning Algorithms
- Stochastic Gradient Descent
- Building a Machine Learning Algorithm
- Challenges Motivating Deep Learning
- Graduates and professionals enrolled for the CAS Advanced Machine Learning
- University or University of Applied Sciences level degree (bachelor, master, phd), Python or other programming experience, some math, statistics and data analysis experience.
- Lectures, tutorials, discussions, project work with presentation.
Practical information (time, location ...)
Time : 2022-08-23 - 26, 09:00 - 12:30
Location : University of Bern, Main Building, room 105.
Language: English
Participants : Max 24
Registration : Mandatory (via Ilias)
Responsible : PD Dr. Sigve Haug
Location : University of Bern, Main Building, room 105.
Language: English
Participants : Max 24
Registration : Mandatory (via Ilias)
Responsible : PD Dr. Sigve Haug
Schedule
Module 1 Machine Learning Review
Tuesday 2022-08-23
09:00 - 09:30 Introduction to Modules 1 and 2
09:30 - 10:30 Introduction to Machine Learning
11:00 - 12:30 Introduction to Machine Learning
12:30 Lunch
13:30 - 17:00 Individual work with notebooks (Notebook 1)
Wednesday 2022-08-24
09:00 - 09:30 Review of notebook and quiz
09:30 - 10:30 Supervised Learning Algorithms
11:00 - 12:30 Supervised Learning Algorithms
12:30 Lunch
13:30 - 17:00 Individual work with notebooks (Notebook 2)
Thursday 2022-08-25
09:00 - 09:30 Review of notebook and quiz
09:30 - 10:30 Unsupervised Learning Algorithms
11:00 - 12:30 Unsupervised Learning Algorithms
12:30 Lunch
13:30 - 17:00 Individual work with notebooks (Notebook 3)
Friday 2022-08-26
09:00 - 09:30 Review of notebook and quiz
09:30 - 10:30 Build a ML algorithm
11:00 - 12:30 Build a ML algorithm
12:30 Lunch
13:30 - 16:00 Individual work with notebooks (Notebook 4)
16:00 - 17:00 Apero
Assessment Days
Each participant or participant group will have 30 minutes to present their module works from Modules 1 and 2. Room and Zoom locations will appear here.
2022-09-21 (with small breaks between the presentations, please group if you like)
13:30 Julian
14:00 Jeremy
14:30 Asad
15:00 James and Martin
15:30 Hop
16:00 Johannes
16:30 Felix
17:00 Julia
17:30 Francesco
18:00 Lucas
18:30 Marco
Alessio on a different day.
Tuesday 2022-08-23
09:00 - 09:30 Introduction to Modules 1 and 2
09:30 - 10:30 Introduction to Machine Learning
11:00 - 12:30 Introduction to Machine Learning
12:30 Lunch
13:30 - 17:00 Individual work with notebooks (Notebook 1)
Wednesday 2022-08-24
09:00 - 09:30 Review of notebook and quiz
09:30 - 10:30 Supervised Learning Algorithms
11:00 - 12:30 Supervised Learning Algorithms
12:30 Lunch
13:30 - 17:00 Individual work with notebooks (Notebook 2)
Thursday 2022-08-25
09:00 - 09:30 Review of notebook and quiz
09:30 - 10:30 Unsupervised Learning Algorithms
11:00 - 12:30 Unsupervised Learning Algorithms
12:30 Lunch
13:30 - 17:00 Individual work with notebooks (Notebook 3)
Friday 2022-08-26
09:00 - 09:30 Review of notebook and quiz
09:30 - 10:30 Build a ML algorithm
11:00 - 12:30 Build a ML algorithm
12:30 Lunch
13:30 - 16:00 Individual work with notebooks (Notebook 4)
16:00 - 17:00 Apero
Assessment Days
Each participant or participant group will have 30 minutes to present their module works from Modules 1 and 2. Room and Zoom locations will appear here.
2022-09-21 (with small breaks between the presentations, please group if you like)
13:30 Julian
14:00 Jeremy
14:30 Asad
15:00 James and Martin
15:30 Hop
16:00 Johannes
16:30 Felix
17:00 Julia
17:30 Francesco
18:00 Lucas
18:30 Marco
Alessio on a different day.
Datasets
During the CAS you ideally work on your own datasets from work, research or private project. However, the lecturers can also you provide you with links to suitable datasets.
Readings
You are not supposed to read many books during this CAS, but of course you can. What you need to consult all the time is online documentation on all topics, google brings you there - and wikipedia of course.
To warm up a bit, you may read Tom Wolfe's account on the rise of the Silicon Valley:
https://web.stanford.edu/class/e145/2007_fall/materials/noyce.html
The technical (Python) skills required are covered in the Python Data Science Handbook: https://jakevdp.github.io/PythonDataScienceHandbook
The CAS content follows more or less the chapters 5 to 20 in the https://www.deeplearningbook.org.
To warm up a bit, you may read Tom Wolfe's account on the rise of the Silicon Valley:
https://web.stanford.edu/class/e145/2007_fall/materials/noyce.html
The technical (Python) skills required are covered in the Python Data Science Handbook: https://jakevdp.github.io/PythonDataScienceHandbook
The CAS content follows more or less the chapters 5 to 20 in the https://www.deeplearningbook.org.
Lecturers and Coaches
Dr. Geraldine Conti (lecturer)
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.
PD Dr. Sigve Haug (director of studies)
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.
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.
PD Dr. Sigve Haug (director of studies)
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.