We are pleased to announce a four-day course to give a hands-on introduction to the field of machine learning using Python. We plan to hold this course on site at ETH Zurich (OCT)
on Thu 16th, Fri 17th, Thu 23rd and Fri 24th March 2023.
The course will be given by Dr. Tarun Chadha, Dr. Franziska Oschmann and Dr. Uwe Schmitt from the Scientific IT Services.
Description
The aim of the course is to provide a robust understanding of the basic concepts of machine learning (focusing on supervised learning) to people with no prior experience in machine learning. During the course the basic concepts of machine learning are introduced by using as little math as possible. Hands-on sessions will allow the users to learn how to use Python for applications of both classical machine learning as well as neural networks methods.
This course is not:
- a comprehensive introduction into the field;
- focusing only on deep learning;
- an introduction to Python.
Preliminary course layout
Thursday, March 16th:
- General introduction
- Concepts of classification
- Overfitting and cross-validation
- How to assess the quality of a classifier
Friday, March 17th:
- Processing-pipelines and hyperparameter optimisation with scikit-learn
- Overview of basic classification algorithms
Thursday, March 23rd:
- Concepts of regression
- Introduction to neural networks and deep learning with TensorFlow
- After the course: Apero
Friday, March 24th:
- Introduction to neural networks and deep learning with TensorFlow (continued)
On all four days we start the lectures/hands-on sessions at 9:30am and expect to end around 3:30pm.
Consultancy sessions
At every course day we will offer an additional 1 hour of data science consultancy where participants can discuss their individual data science problems, questions and projects with the tutors.
The consultancy sessions take place after the official course hours from 4 to 5pm and are voluntary.
Apero
We invite all participants to an Apero after the course on the 23rd of March. We would like to take this opportunity for personal and professional exchange and encourage all participants to join.
Requirements
You need to have some basic understanding of Python. No working experience of machine learning is expected.
Participation and registration fees
This course is open to the following members of ETH Zurich: PhD students, postdocs, scientific/technical staff, professors. Bachelor/master students are not eligible to participate in this course. The maximal number of participants is 30, filled on a "first come, first served" basis. Surplus registrations will form a waiting list.
The registration fee for the course is 400CHF. Please note that we only accept credit card payments.
Important note: For SIS subscription customers this course is free of charge; in this case the course fee is just a deposit and will be refunded to the participant after the course if he/she has attended the full course. If you are unsure, please check with your PI whether your group/department has a SIS subscription. Please note that being a member of an HPC shareholdership on Euler/Leonhard or making use of our RDM/openBIS service alone do not suffice for free participation.
Application
To apply for the course please fill out the application form.
In case of questions, contact Franziska Oschmann or Uwe Schmitt.
FAQ 1. Is my group or department a SIS subscription customer?
Please check with your PI to see if your research group is a SIS subscriber. Note that for some departments we have departmental subscriptions. Your PI should know about this. Please note that membership in an HPC shareholder group on Euler or use of our RDM/openBIS service alone is not sufficient for free participation. For students/staff from the departments/research groups listed above, the course is free. In this case, the course fee is only a deposit and will be refunded to the participant after the course if she/he has attended the entire course.
2. Do you plan to offer the course again?
We offer this course once per year and the next iteration is planned for spring 2024.
3. Is it possible to attend only a part of the course / to miss a part of the course?
We expect full attendance at the course. Otherwise, we can not grant a certificate or reimburse the course fee in case you are a SIS subscription customer.
4. Can I join remotely?
The course is planned to be held on-site without the option to join remotely. We will also not offer a recording of the course.
5. Is the course rewarded with ECTS credits?
We can not grant ECTS for this course as we are not part of the official ETH course catalogue. However, every participant, who attended the full course, will get a certificate.