👩‍💼

IntroML workshop July 2022

Attachment

Author

Date

Last edited time

Nov 23, 2022 12:34 PM

URL

🔻

Slides and interactive notebook available

Format

What? An in-person, hands-on, free workshop introducing machine learning
For whom? PhD students, postdocs, and PIs affiliated with the University of Tübingen
When? July 6th, 2022, from 9:00 to 17:00 (with pauses)
Where? Max Planck Institute for Intelligent Systems, Lecture hall (ground floor), Max-Planck-Ring 4, 72076 Tübingen
Instructors? Alexandra Gessner, 👤Seth Axen, , @ML ⇌ Science Colaboratory, Cluster of Excellence ML for Science.

Content

In the tutorial part, we will discuss with the aid of interactive demonstrations topics such as

Foundational ML notions: data features, model complexity, generalization, evaluation of performance, ...
Neural networks: gradient-based training, feature extraction, architectures, transfer learning, …
Data types: text, time series, relational data, images, ...
Programming ML models vs. traditional software.
The ML workflow in practice, from data collection to performance evaluation.
Limitations of ML for science.

In the workshop part, we will jointly look at specific use-cases brought by the attendees and discuss how to design ML projects to address them.

Prerequisites

Scholars from all disciplines are warmly invited to join; no math or programming skills will be assumed.
Bring your own laptop, and please check your eduroam config before coming!
In connection to one of your research problems, think about the characteristics of relevant datasets that you have access to (how many records, what fields? ...) and what you’d like ML to help with. Be ready to discuss your use-case with the group in one single slide; we will provide suggestions to help you make a practical machine learning project out of it.

Logistics

How to get to the Max-Planck Institute für Intelligente Systeme (MPI-IS)

Max-Planck-Ring, 4. There are rain-protected bicycle parking spots.

Take bus #3 and stop at “Max-Planck-Institute”. Walk down the Paul-Ehrlich-Straße and then take the Max-Planck-Ring on your left, or walk the blue path between the buildings.

You may have to ring at the main door to be let in.

Alternatively, take bus #4 to stop “Corrensstraße”, and climb the stairs across the street. You are looking for the black building.

Where to eat nearby?

We’ll have a 1h lunch pause around noon. There are a couple of places with vegetarian options:

Indian Spicetripping Foodtruck. Let us know by July, 5th so that we reserve it in advance!
Yellow Donkey. Greek-style food, nice sitting options.

Please think of bringing an empty lunch box (e.g. rebowl) with you, and cutlery!

Format

What? An in-person, hands-on, free workshop introducing machine learning

For whom? PhD students, postdocs, and PIs affiliated with the University of Tübingen

When? July 6th, 2022, from 9:00 to 17:00 (with pauses)

Where? Max Planck Institute for Intelligent Systems, Lecture hall (ground floor), Max-Planck-Ring 4, 72076 Tübingen

Instructors? Alexandra Gessner, 👤Seth Axen, , @ML ⇌ Science Colaboratory, Cluster of Excellence ML for Science.

Content

In the tutorial part, we will discuss with the aid of interactive demonstrations topics such as

Foundational ML notions: data features, model complexity, generalization, evaluation of performance, ...

Neural networks: gradient-based training, feature extraction, architectures, transfer learning, …

Data types: text, time series, relational data, images, ...

Programming ML models vs. traditional software.

The ML workflow in practice, from data collection to performance evaluation.

Limitations of ML for science.

In the workshop part, we will jointly look at specific use-cases brought by the attendees and discuss how to design ML projects to address them.

Prerequisites

Scholars from all disciplines are warmly invited to join; no math or programming skills will be assumed.

Bring your own laptop, and please check your eduroam config before coming!

In connection to one of your research problems, think about the characteristics of relevant datasets that you have access to (how many records, what fields? ...) and what you’d like ML to help with. Be ready to discuss your use-case with the group in one single slide; we will provide suggestions to help you make a practical machine learning project out of it.