The AI & Physics track at AMLD2021 will focus on specific subdomains that target improving physics data analysis with the tools of ML and understanding ML models with the tools of physics. The track will contain three sub-sessions covering (i) inference and anomaly detection, (ii) Statistical Physics for understanding ML, (iii) ML for quantum technologies. These topics address key questions of how AI can improve the capability to perform scientific measurements and identify spurious signatures that may be signs of new physical behavior, how ML in the high dimensional limit can be understood through the lens of theoretical physics, and how ML can inform the design and control of quantum experiments.

Machine learning and physics have a symbiotic and transformative influence on each other, leading to profound changes in approaches to physics and ML and thus paving the way to tackle previously intractable problems and to exploit new capabilities. The objective of covering these topics is on the one hand to investigate how ML can optimise the design, control, and information extraction of experiments and to speed up compute-intensive tasks which limit research capabilities. On the other, theoretical tools from physics provide a means to extract information about ML models and their learning dynamics. Thus this track aims to explore the questions: How can we best extract insights from physics data and make use of powerful physics models and high fidelity simulators whilst ensuring such methods are well calibrated? Can we harness the capabilities of ML to automate the delicate design and data collection of quantum experiments? Can we describe the dynamics of neural networks from a first principles understanding?

We invite you (researchers and practitioners) to submit your contributions for the next AI & Physics track at AMLD. Accepted submissions will be selected for short oral presentation or for poster presentation.

Help us to make this track a great interdisciplinary session in one of the largest machine learning and AI events in Europe!

About your presentation

• Language: all presentations are in English
• Duration: we would like to keep the sessions interesting, full of energy and fast-paced, thus we’re looking for talks of a length of approximately 10 minutes. We will be on a tight schedule and will enforce the time limits rigorously. We suggest that you time your presentation in advance.
• Audience: your public will be made of researchers, practitioners, students, with different levels of knowledge and expertise. We suggest not to dig into very technical details. Still, feel free to provide references and pointers in case someone is interested in investigating further!
• Focus: the best presentations have a point. And one point only. Keep both your talk and its proposal concise and focused. A rule of thumb is the following: if you need more than three paragraphs for your proposal, try to reduce its scope. This will help us to deal with the massive amount of submissions we get, help you to streamline your presentation, and help the audience retain the most out of your talk.
• Originality: one of the things we want to do at AMLD is to push the community forward. Thus, we favor original content. If you want to present a topic that you have talked about elsewhere, try to add a twist, new research or development to it – something to make it unique.

Selection process

Here’s how presentations will be selected:

All submissions are reviewed and voted for by the conference and track organizers. Each presentation is rated on a scale from 1 to 10 by different reviewers, and the marks are averaged. The evaluation takes into account the following criteria:

1. relevance of the topic to the ML community and for the track
2. coherence and clarity of the proposal
3. novelty/originality of the topic
4. consistency with the time limits

Video recording for presentations

We plan to record and publish all talks online for free, along with a recording of the slide deck, live demo, and any on-presenter-screen activity. We do this for the benefit of the larger ML community and those who couldn’t make it to the conference. Since you retain full ownership of your slides and recording, we’d like to ask you to make your materials and recording available under a Creative Commons (we default to non-commercial reuse) or other open source licenses.
We hope you agree with us, but if you are uncomfortable with this in any way, let us know.

If in doubt, reach out! If you have an idea for a presentation but are unsure, please talk to us! Reach out to info@appliedmldays.org.

Apply now by filling this form