In the next few days I have a busy schedule with a few lectures gravitating around the use of deep learning technologies for fundamental physics research. This is of course no news, but I thought that my blog is the proper place to list a few pointers, in case some of you is interested in following one or two of these events. After all, deep learning is all the rage these days, and even if fundamental physics is not your bread and butter, you may hopefully find useful inspiration in the kind of use cases that field provides for cutting edge applications of artificial intelligence.

The first event takes place tomorrow morning, at 11AM CET. This is not a good time if you live in the new world, alas. I will be giving a seminar in Lund University, where I have traveled yesterday to find a rather Swedish weather and, to my surprise, a practical absence of reminders that we are (still) in the middle of a pandemic. I will speak on "Toward the end-to-end optimization of experimental design with differentiable programming", with the following abstract:

"In the past few decades particle physics has made giant leaps by studying matter at the shortest distance scales with detectors built on a few paradigms which worked very well, but which today look increasingly misaligned with the progress of information-extraction procedures, as the construction choices of complex apparatus live in hundreds-dimensional parameter spaces which until recently humans have been unable to probe systematically.
The result of not investigating the full space of solutions to particle detection, pattern recognition, and inference extraction is a huge potential loss in performance. Our saviour may be differentiable programming, which exploits the formulation of continuous models of all the ingredients of measurements in fundamental physics, as well as, crucially, a carefully constructed objective function. Backpropagation through a differentiable pipeline of all the elements of the problem may then allow us to probe the design space and realign design and goals of experiments that base their operation on the interaction of radiation with matter, besides finding entirely new ways to solve our detection problems. In this seminar I will illustrate how we can set out to create the interfaces to solve our difficult optimization problems, with great prospects for future endeavours in HEP, astro-HEP, nuclear and neutrino physics when these allow for time and resources to carry out such studies."
The seminar can be followed via zoom at this link - but you will need a password, which I will be happy to give you if you email me at tommaso(dot)dorigo(at)gmail(dot)com.

Just hours after my return to Italy, in the morning of November 5 I will give a talk of similar content, but more technical nature, at a Workshop on Muon Collider that takes place in Padova. To follow that presentation you will need to register to the workshop (it's free).

The day after, on November 6, I will be (virtually) in Iran for a lecture on the starting day of the yearly USERN congress. In fact my talk will open the works there... The title of my presentation is "Searching in the Dark: Unsupervised Learning Meets Fundamental Science". I do not have a link to share on this event yet, but I will update this page as soon as I do.

Two days later I will give a presentation on an anomaly detection algorithm I developed, RanBox, at the CMS Statistics Committee. That presentation is not publically accessible, as it is an internal CMS experiment meeting... I list it here only because I fear I will forget to attend it otherwise! (Yes, these things do happen - the last such disaster was not more than three months ago! :( ).

On November 11 the USERN congress will also feature a mini-workshop on the topic of "Artificial Intelligence Challenges for Science and Society". I will chair and introduce that event, which will feature presentations by Prof. Mauro Da Lio, Prof. Christoph Weniger, and Dr. Pietro Vischia. Again, no link to share yet, but it will soon become available.

And finally, on November 22 I will give a two-hour lecture on Machine Learning for particle physics at the ICTS SUSY Hunting school. Again, not an event you will want or have a chance to follow, but it makes this list because it's in my agenda...


Tommaso Dorigo (see his personal web page here) is an experimental particle physicist who works for the INFN and the University of Padova, and collaborates with the CMS experiment at the CERN LHC. He coordinates the MODE Collaboration, a group of physicists and computer scientists from eight institutions in Europe and the US who aim to enable end-to-end optimization of detector design with differentiable programming. Dorigo is an editor of the journals Reviews in Physics and Physics Open. In 2016 Dorigo published the book "Anomaly! Collider Physics and the Quest for New Phenomena at Fermilab", an insider view of the sociology of big particle physics experiments. You can get a copy of the book on Amazon, or contact him to get a free pdf copy if you have limited financial means.