Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

CERN uses ultra-compact AI models on FPGAs for real-time LHC data filtering

theopenreader.org

Post reply on HN
Print view View original

161–166 of 166 posts

Re: CERN uses ultra-compact AI models on FPGAs for real-time LHC data filtering

#161

Post by mpierini »

tasuki wrote: post #89
idiotsecant wrote: post #80

Earlier quoted context omitted.

Some career do-nothing-but-make-noise in my organization hired a firm to 'Do AI' on some shitty data and the outcome was basically linear regression. It turns out that you can impressive executives with linear regression if you deliver it enthusiastically enough.

Tbh, often enough, linear regression is exactly what is needed.

And you think we did not try linear regressions? This is what we used to do 20 years ago. Then we gained two orders of magnitude in signal-to-background discrimination. And since our data are not even images, off-shelf solutions mostly don’t apply. Try to process40 MHz of incoming collisions (1 MB each) within 100 nsec with a linear regression of point-cloud data. When you are done trying, try to think that maybe (maybe…) life is not as easy as bread&butter. If you succeed, come and knock at CERN’s door. Maybe we will let you in…

Re: CERN uses ultra-compact AI models on FPGAs for real-time LHC data filtering

#162

Post by mpierini »

thesz wrote: post #97
dcanelhas wrote: post #32

Earlier quoted context omitted.

I'm half expecting to see "AI model" appearing as stand-in for "linear regression" at this point in the cycle.

There is an HIGGS dataset [1]. As name suggest, it is designed to apply machine learning to recognize Higgs bozon. [1] https://archive.ics.uci.edu/ml/datasets/HIGGS In my experiments, linear regression with extended (addition of squared values) attributes is very much competitive in accuracy terms with reported MLP accuracy.

And this problem is a joke compared to a real problem. We are talking about going from 40 MHz to 100 kHz incoming data stream, after which a second layer of real-time selection reduces the data to 1 kHz which is processed, cleaned, elaborated into high level features that you have in that dataset. But if you think you can do better, apply for a CERN job, come here and enlighten us!

Re: CERN uses ultra-compact AI models on FPGAs for real-time LHC data filtering

#163

Post by mpierini »

thesz wrote: post #140
dguest wrote: post #99

Earlier quoted context omitted.

The LHC has moved on a bit since then. Here's an open dataset that one collaboration used to train a transformer: https://opendata-qa.cern.ch/record/93940 if you can beat it with linear regression we'd be happy to know.

Thanks. The paper [1] referenced in your link follows the lagacy of the paper on the HIGGS dataset, and does not operate with quantities like accuracy and/or perplexity. HIGGS dataset paper provided area under ROC, from which one had to approximate accuracy. I used accuracy from the ADMM paper [2] to compare my results with. As I checked later, area under ROC in [1] mostly agrees with [2] SGD training results on HIGG…

Perplexity, aka measuring how much a network is sure about its answer. Which might be wrong. It would not pass the pier review of any particle physics journal. (Real) science is about being right, not about being sure about itself.

Re: CERN uses ultra-compact AI models on FPGAs for real-time LHC data filtering

#164

Post by mpierini »

amelius wrote: post #88
jurschreuder wrote: post #77

I've got news for you, everybody with a modern cpu uses this, which use a perceptron for branch prediction.

At this point AI basically means "we didn't know how to solve the problem so we just threw a black box at it".

Wrong! We do how to solve the problem, but the solution does not run on an electronic board at 100 nsec. So it has to be approximated with a function that runs within that time constraint. Also, if deciding to accept/reject events based on a learned metric of typicality is not AI, then why guessing the next token is AI? We have robots going around the LHC tunnel fixing things in high radiation environment. Is that enough AI? If not, we accept volunteers to replace the robots… Relax people and try to imagine that life might be more complicated than what an oversimplified general public article says

Re: CERN uses ultra-compact AI models on FPGAs for real-time LHC data filtering

#165

Post by mpierini »

idiotsecant wrote: post #117
tasuki wrote: post #89

Earlier quoted context omitted.

Tbh, often enough, linear regression is exactly what is needed.

Yes, and we do it every day and call it 'linear regression' and don't need a data center full of expensive toys to do it

You do unsupervised learning without labels with a linear regression. Interesting. What would you regress in this case? The problem is the following: you have a point cloud of data (electronic signal from arrays arranged into an irregular pattern). You know the physics that was discovered. You are looking for rare events (one in a billion or less) and you don’t know what they look like.

Re: CERN uses ultra-compact AI models on FPGAs for real-time LHC data filtering

#166

Post by mpierini »

ozim wrote: post #152
idiotsecant wrote: post #150

Earlier quoted context omitted.

Implement it...from scratch? Its literally least squares regression. Its a few lines of code. What are you trying to say here?

You have to get the data first build all data processing pipelines to get your parameters for linear regression.

A lot of data. More than google + netflix + you name it. And you have 100 nsec. And the data are not on disk. Good luck with your linear regression
Post reply on HN