@dlphysics

Working hard to pass a turing exam

deeplearnphysics.org
Joined December 2017
  • Tweets106
  • Following30
  • Followers154
11Media
deeplearnphysics retweeted
Kyle Cranmer
@KyleCranmer5 Nov 2021
Submitted! The new chapter on Machine Learning for the Particle Data Group. The PDG provides very useful reviews on a variety of topics ranging from summaries of experimental results, theoretical models, mathematical tools, etc. w/ @codingkazu @seljakuros pdg.lbl.gov/2021/reviews/con…
8
30
4
215
Shout out to Francois presenting our end-to-end #ML chain for 3D #LArTPC images at #NeurIPS2020 ML4Phys workshop today! This chain is being implemented for analyzing 3D #neutrino images from the #DUNE experiment! Paper tinyurl.com/neutrino-3d-pape… Poster tinyurl.com/neutrino-3d-post…
1
1
NPML is holding a satellite workshop to Neutrino 2020 conference to promote young researchers to tell us about their ML research in neutrino physics. Big applause to the day 1 speakers, hyper bright students and postdocs! indico.slac.stanford.edu/eve…
1
1
Laura Domine put up a technical demo paper of @facebookai Sparse Submanifold Conv. Net (SSCN). SSCN is a fantastic fit for #LArTPC data which is sparse but locally dense and has a rich 1D structure in 2D/3D data. Scalable #DeepLearning for #LArTPC! arxiv.org/abs/1903.05663

Scalable Deep Convolutional Neural Networks for Sparse, Locally...

Deep convolutional neural networks (CNNs) show strong promise for analyzing scientific data in many domains including particle imaging detectors such as a liquid argon time projection chamber...

arxiv.org
1
1
deeplearnphysics retweeted
Blake Richards@tyrell_turing26 Feb 2019
This is one of my favourite papers in recent years - now out in eLife! All those "non-responsive" (i.e. flat PSTH) neurons? They may actually be doing something. It's almost like the brain wasn't designed to be human interpretable! ;) doi.org/10.7554/eLife.42409

Spike-timing-dependent ensemble encoding by non-classically responsive cortical neurons

During behavior, many neurons do not have classic trial-averaged responses to behaviorally relevant stimuli, but can still have activity and population dynamics related to stimulus and behavioral...

elifesciences.org
5
53
7
162
Almost a month late but #MachineLearning paper lead by a few of our collaborators in @Microboone #neutrino #physics experiment made it to Department of Energy #Science #Highlights! science.energy.gov/hep/highl…
2
5
deeplearnphysics retweeted
Josh Gordon@random_forests26 Feb 2019
Good news! TensorBoard now works in Jupyter Notebooks, via magic commands "%" that match the command line. Example: colab.research.google.com/gi…
25
412
45
1,291
Better to revive twitter feeds :) @gnperdue gave a full overview of Quantum Information System (#QIS) overview at @SLAClab mini QIS workshop. Thanks Gabe! We learned a lot! indico.slac.stanford.edu/eve…

Emerging Opportunities in Quantum Machine Learning & Quantum Algorithms

indico.slac.stanford.edu
1
Convolutional #NeuralNetworks applied for background rejection for liquid scintillator detector like KamLAND type. Shout out to Aobo Li and the team of physicists from BU, U Chicago and MIT! arxiv.org/abs/1812.02906

Suppression of Cosmic Muon Spallation Backgrounds in Liquid...

Cosmic muon spallation backgrounds are ubiquitous in low-background experiments. For liquid scintillator-based experiments searching for neutrinoless double-beta decay, the spallation product...

arxiv.org
2
Two teams from our group were there, LArbys and SBNfit! Thanks to all sponsors and @BrookhavenLab for hosting this very productive week! Accelerated Computing Hackathon Returns for Second Year bnl.gov/newsroom/news.php?a=… via @BrookhavenLab

Accelerated Computing Hackathon Returns for Second Year

Brookhaven’s Computational Science Initiative hosted its second hackathon on graphics processing units for accelerating scientific discovery.

bnl.gov
deeplearnphysics retweeted
hardmaru
@hardmaru8 Dec 2018
Our work on “Deep Learning for Classical Japanese Literature” is out! We introduce Kuzushiji-MNIST, a drop-in replacement for MNIST, plus 2 other datasets. In this work, we also try more interesting tasks like domain transfer from old Kanji to new Kanji. arxiv.org/abs/1812.01718
9
279
21
887
Being silent for long time! Restarting tweets with #DataScientist #job opportunities at @SLAClab for the search of #DarkMatter in LZ experiment using #NERSC high performance computing (HPC) cluster! RA (postdoc): academicjobsonline.org/ajo/j… SW developer: academicjobsonline.org/ajo/j…
Want to be a #physics professor *and* apply #MachineLearning for neutrino physics? A faculty job opportunity at University of Pittsburg is coming out! You'll get to analyze beautiful #particle images from #TPC! Contact for more details... main.hercjobs.org/jobs/11483…
1
... and how to preprocess data on GPU! deeplearnphysics.org/Blog/20…
1
1
Many of us got a lot out of #GPU #hackathon at @BrookhavenLab! Our graduate student Laura Domine wrote blog posts on how to write custom #cuDA kernels for our #MachineLearning algorithms. Part 1 deeplearnphysics.org/Blog/20… Part 2 deeplearnphysics.org/Blog/20…
Another interesting data set! github.com/Microsoft/USBuild… "This dataset contains 125,192,184 computer generated building footprints in all 50 US states. This data is freely available for download and use." nytimes.com/interactive/2018…
NASA is using HoloLens AR headsets to build its new spacecraft faster - via @techreview technologyreview.com/s/61224…

NASA is using HoloLens AR headsets to build its new spacecraft faster

Lockheed Martin engineers wear the goggles to help them assemble the crew capsule Orion—without having to read thousands of pages of paper instructions.

technologyreview.com
1
1
Updated version of containers with #TensorFlow v1.11.0 (new) and #PyTorch v0.4.1 (same), built and made available singularity-hub.org/collecti… via @SingularityApp
5
9
Very short notice (sorry!) for those who are at @SLAClab and @Stanford, today's particle theory seminar invites a physicist from @UCBerkeley talking about "a Framework for Unsupervised #MachineLearning in Particle Physics (JUNIPER)". Come and enjoy! theory.slac.stanford.edu/eve…
Want to look where your #MachineLearning algorithm spending compute time and memory? Corey Adams wrote a tutorial blog post on profiling #TensorFlow with #TensorBoard. Check it out! deeplearnphysics.org/Blog/20…
2
Load more