ML2R Autumn School – Get Packing!

Boxing day comes early this year: ML2R invites you to the 2021 autumn school!

Join the ML2R autumn school on October 4th to 8th, 2021!

Learn about the industry-relevant problem of bin packing and work together with like-minded researchers to develop a Machine Learning approach. Postage has already been paid – participation is free! All attendees will receive a certificate and prices will be awarded to different categories of winning teams.

Learn from experts about a relevant industry problem

Meet like-minded people

Create novel Machine Learning solutions together.

What is behind the bin packing problem?

We all enjoy the occasional game of Tetris. But unfortunately or luckily, the world offers more than just seven shapes and a single rectangle to put them on. One of the simplest definitions of the bin packing problem can be stated thus: Given a set of items (each associated with a volume) and a set of containers (each associated with a finite capacity), decide if there exists a configuration where all items fit into the containers.

Bin packing is a member of the NP-complete set of problems. As it is with NP-complete problems, assessing the quality of a solution is not the problem, obtaining a provably good solution is the hard part.

Bin packing has been studied thoroughly from both theoretical and practical perspectives under numerous sets of constraints. Bins need not be of a standardized size, their number can be severely limited, packages may not only be described by a volume but also by a weight or monetary value … the list is endless. But often these constraints are dictated by a real practical application.

Learn more in our recent post “Bin packing: When even Computers have to guess” published in the ML2R Machine Learning blog.

A combination of theory, practice, and a friendly competition

During the autumn school, you will gain a deeper understanding of the bin packing problem itself and get to know a variety of approaches to tackle it. But not only that: Sitting through a week of lectures without practice is no fun, even less in an online setting. Therefore, the event will be a mix of theory and practice. Lectures and keynotes provide the necessary basis, but you will spend a large portion of the time working together in small groups. This will give you the chance to apply your Machine Learning skills to a well-defined version of the bin packing problem and to gain new perspectives on combinatorial optimization. Ultimately, the autumn school will be about learning together and connecting with others. On top of that, bin packing also lends itself very well to a friendly competition.

Participation is free but the number of slots is limited. If you are a Master student or a PhD student knowledgeable in Machine Learning and Data Science and want to participate, please apply via the form below until September 5th, 2021. We will review applications and notify you on the outcome in the second week of September.

Agenda

It is expected that workshops will take place within the timeframe of 10:00 a.m. to 05:00 p.m. CEST (Central European Summer Time) / UTC +2 (Coordinated Universal Time)

Monday
    • Introduction to bin packing and its theoretical foundation
    • Existing (Machine Learning) approaches to the problem of bin packing
    • It’s time to get to know everyone! Socializing and team building
Tuesday
    • First steps towards coding for bin packing
    • Selected Design Thinking methods to support your progress as a group
    • Time to shuffle the boxes! We will be available for questions throughout the day
    • Recreational evening program: data driven drink delectation
Wednesday
    • MLOps: how to go from prototype to deployment
    • More time to get stacking!
    • Game Night
Thursday
    • Time to teach your algorithm to pack the boxes
    • Solution deadline
    • Graduation party: let’s celebrate the submission of your solution!
Friday
    • Prepare to present your solutions
    • Ask me anything: meet software engineers, post-docs, and PhD students
    • The big final hour: presentations and award ceremony

Contact

Vanessa Toborek & Sebastian Müller

Key Points

What

Bin packing: theory and practice

When

October 4th to 8th, 2021, Time zone: CEST

Who

Master and PhD students knowledgable in Machine Learning and Data Science

Where

Online

Why

Receive a certificate for participation and win awesome prizes!

Deadline: September 5th, 2021

Contact

Vanessa Toborek & Sebastian Müller

Key Points

What

Bin packing: theory and practice

When

October 4th to 8th, 2021, Time zone: CEST

Who

Master and PhD students knowledgable in Machine Learning and Data Science

Where

Online

Why

Receive a certificate for participation and win awesome prizes!

Deadline: September 5th, 2021

Application form

Required
Required
Bitte füllen Sie das Pflichtfeld aus.
Bitte füllen Sie das Pflichtfeld aus.
Bitte füllen Sie das Pflichtfeld aus.
Required
Required
Required
Required


In the future, we will use the e-mail address you have provided to inform you by e-mail about our own similar offers (e.g. events). You can object to this use at any time by contacting Fraunhofer, in particular at widerspruch@iais.fraunhofer.de . You can access further information on the subject of data protection at Fraunhofer, in particular on the legally prescribed information obligations, at any time via our data protection policy.


In the future, we will use the e-mail address you have provided to inform you by e-mail about our own similar offers (e.g. events). You can object to this use at any time by contacting Fraunhofer, in particular at widerspruch@iais.fraunhofer.de . You can access further information on the subject of data protection at Fraunhofer, in particular on the legally prescribed information obligations, at any time via our data protection policy.

Autumn School Team

Fouad Alkhoury

Sebastian Müller

Till Schulz

Vanessa Toborek

Pascal Welke

In cooperation with

The KI Lernlabor (Artificial Intelligence Learning Lab) supports small and medium-sized enterprises in getting started with Artificial Intelligence, learning about practical applications and qualifying employees.