Skip to content

Commit 2df1149

Browse files
committed
update
1 parent 1f5553a commit 2df1149

3 files changed

Lines changed: 40 additions & 21 deletions

File tree

index.html

Lines changed: 6 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -66,38 +66,32 @@ <h2>Learn more!</h2>
6666
<div class="box" height=375>
6767
<p>An article in the CERN Courier on "Hunting anomalies with an AI trigger"</p>
6868
<a href="https://cerncourier.com/a/hunting-anomalies-with-an-ai-trigger/" class="button">CERN Courier</a>
69-
</div>
70-
</div>
71-
72-
<div class="column2">
73-
<a href="#" class="image image-full"><img src="images/8.jpeg" width=282 alt="" /></a>
74-
<div class="box" height=375>
75-
<p>Cover of August 2021 issue of Nature Machine Intelligence</p>
7669
<a href="https://www.nature.com/natmachintell/volumes/3/issues/8" class="button">Nat. Mach. Intell.</a>
70+
<a href="https://home.cern/news/news/physics/speeding-machine-learning-particle-physics" class="button">CERN News</a>
7771
</div>
7872
</div>
79-
<div class="column3">
73+
<div class="column2">
8074
<a href="#" class="image image-full"><img src="images/mlperf.png" width=282 alt="" /></a>
8175
<div class="box" height=375>
8276
<p>hls4ml team submits results for the first Tiny MLPerf Inference Benchmark</p>
8377
<a href="https://mlcommons.org/en/news/mlperf-tiny-v05/" class="button">Tiny MLPerf</a>
8478
</div>
8579
</div>
86-
<div class="column1">
80+
<div class="column3">
8781
<a href="#" class="image image-full"><img src="images/hls4ml.png" width=282 alt="" /></a>
8882
<div class="box" height=375>
8983
<p>hls4ml: an open-source code framework for translating machine learning algorithms directly into FPGA firmware</p>
9084
<a href="https://fastmachinelearning.org/hls4ml/" class="button">hls4ml home</a>
9185
</div>
9286
</div>
93-
<div class="column2">
87+
<div class="column4">
9488
<a href="#" class="image image-full"><img src="images/xilinx.png" width=282 alt="" /></a>
9589
<div class="box" height=375>
9690
<p>A story from Xilinx on how we use high level synthesis to find the best events at the Large Hadron Collider</p>
9791
<a href="https://www.xilinx.com/publications/powered-by-xilinx/cerncasestudy-final.pdf" class="button">Visit Xilinx</a>
9892
</div>
9993
</div>
100-
<div class="column3">
94+
<div class="column1">
10195
<a href="#" class="image image-full"><img src="images/azure.png" width=282 alt="" /></a>
10296
<div class="box" height=375>
10397
<p>Microsoft Azure collaboration deploying FPGAs to accelerate ML to prototype computing solutions for future big science experiments</p>
@@ -106,7 +100,7 @@ <h2>Learn more!</h2>
106100
<a href="http://news.mit.edu/2019/boosting-computing-power-for-future-particle-physics-mit-lns-0819" class="button"Visit>MIT News</a>
107101
</div>
108102
</div>
109-
<div class="column1">
103+
<div class="column2">
110104
<a href="#" class="image image-full"><img src="images/zenuity.png" width=282 alt="" /></a>
111105
<div class="box" height=375>
112106
<p>Zenuity has become the first automotive to team up with CERN to develop ML for autonomous drive cars</p>

people.html

Lines changed: 13 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -306,16 +306,28 @@ <h3> UC San Diego </h3>
306306
<a href="javascript:showhide('rkansal')"> Raghav Kansal</a> (Graduate, Physics);
307307
<a href="javascript:showhide('fmokhtar')"> Farouk Mokhtar</a> (Graduate, Physics);
308308
<a href="javascript:showhide('vrazavim')"> Vesal Razavimaleki</a> (Undergraduate, Engineering Physics);
309+
<a href="javascript:showhide('rroy')"> Rushil Roy</a> (Undergraduate, Electrical Engineering);
310+
<a href="javascript:showhide('jliang')"> Jason Liang</a> (Undergraduate, Electrical Engineering);
311+
<a href="javascript:showhide('tnguyen')"> Tai Nguyen</a> (Undergraduate, Physics);
312+
<a href="javascript:showhide('rkastner')"> Ryan Kastner</a> (PhD, Computer Science);
313+
<a href="javascript:showhide('oweng')"> Olivia Weng</a> (Graduate, Computer Science and Engineering)
309314
<div id="jduarte" style="display:none;">
310315
<ul>
311316
<li> <b>Position</b>: Assistant Professor </li>
312317
<li> <b>Interests</b>: Higgs boson, trigger, graph neural networks, selective persistence, data scouting, anomaly detection </li>
313318
</ul>
314319
<a href="images/javier_duarte.jpg" class="image image-centered"><img src="images/javier_duarte.jpg" height="300" alt="" /></a>
320+
</div>
321+
<div id="ddiaz" style="display:none;">
322+
<ul>
323+
<li> <b>Position</b>: Postdoc </li>
324+
<li> <b>Interests</b>: level-1 trigger, missing transverse momentum </li>
325+
</ul>
326+
<a href="images/Daniel_Diaz.jpg" class="image image-centered"><img src="images/Daniel_Diaz.jpg" height="300" alt="" /></a>
315327
</div>
316328
<div id="vrazavim" style="display:none;">
317329
<ul>
318-
<li> <b>Position</b>: Undergradauate Student </li>
330+
<li> <b>Position</b>: Undergraduate Student </li>
319331
<li> <b>Interests</b>: graph neural networks, tracking </li>
320332
</ul>
321333
<a href="images/Vesal_Razavimaleki.jpg" class="image image-centered"><img src="images/Vesal_Razavimaleki.jpg" height="300" alt="" /></a>

projects.html

Lines changed: 21 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -48,24 +48,37 @@ <h2>Projects</h2>
4848
<h3> Papers </h3>
4949
<p style="line-height:1.3">
5050
<ul>
51-
<li> GPU-accelerated machine learning inference as a service for computing in neutrino experiments, <a href="https://arxiv.org/abs/2009.04509">arXiv:2009.04509</a> [physics.comp-ph]. </li>
52-
<li> Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics, <a href="https://arxiv.org/abs/2008.03601">arXiv:2008.03601</a> [physics.comp-ph]. </li>
53-
<li> GPU coprocessors as a service for deep learning inference in high energy physics, <a href="https://arxiv.org/abs/2007.10359">arXiv:2007.10539</a> [physics.comp-ph]. </li>
54-
<li> Ultra Low-latency, Low-area Inference Accelerators using Heterogeneous Deep Quantization with QKeras and hls4ml, <a href="https://arxiv.org/abs/2006.10159">arXiv:2006.10159</a> [physics.ins-det]. </li>
55-
<li> Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml, <a href="https://doi.org/10.1088/2632-2153/aba042">MLST (2020)</a>. </li>
51+
<li> Real-time Artificial Intelligence for Accelerator Control: A Study at the Fermilab Booster, <a href="https://arxiv.org/abs/2011.07371">arXiv:2011.07371</a>. </li>
52+
<li> A reconfigurable neural network ASIC for detector front-end data compression at the HL-LHC, <a href="https://10.1109/TNS.2021.3087100">IEEE Trans. Nucl. Sci. 68, 2179 (2021)</a>. </li>
53+
<li> Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider, <a href="https://arxiv.org/abs/2108.03986">arXiv:2108.03986</a>. </li>
54+
<li> Accelerating Recurrent Neural Networks for Gravitational Wave Experiments, <a href="https://arxiv.org/abs/2106.14089">arXiv:2106.14089</a>. </li>
55+
<li> Fast convolutional neural networks on FPGAs with hls4ml, <a href="https://doi.org/10.1088/2632-2153/ac0ea1">Mach. Learn.: Sci. Technol. 2, 045015 (2021)</a>. </li>
56+
<li> MLPerf Tiny Benchmark, <a href="https://arxiv.org/abs/2106.07597">arXiv:2106.07597</a>. </li>
57+
<li> hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices, <a href="https://arxiv.org/abs/2103.05579">arXiv:2103.05579</a>. </li>
58+
<li> GPU-accelerated machine learning inference as a service for computing in neutrino experiments, <a href="https://doi.org/10.1038/s42256-021-00356-5">Nat. Mach. Intell. 3, 675 (2021)</a>. </li>
59+
<li> Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics, <a href="https://arxiv.org/abs/2008.03601">arXiv:2008.03601</a>. </li>
60+
<li> GPU coprocessors as a service for deep learning inference in high energy physics, <a href="https://arxiv.org/abs/2007.10359">arXiv:2007.10539</a>. </li>
61+
<li> Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors, <a href="https://arxiv.org/abs/2006.10159">arXiv:2006.10159</a>. </li>
62+
<li> Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml, <a href="https://doi.org/10.1088/2632-2153/aba042">Mach. Learn.: Sci. Technol. 2, 015001 (2021)</a>. </li>
5663
<li> Fast inference of Boosted Decision Trees in FPGAs for particle physics, <a href="https://doi.org/10.1088/1748-0221/15/05/p05026">JINST 15, P05026 (2020)</a>. </li>
57-
<li> ESP4ML: Platform-Based Design of Systems-on-Chip for Embedded Machine Learning, <a href="https://sld.cs.columbia.edu/pubs/giri_date20.pdf"> DATE Conference 2020 </a>.
64+
<li> ESP4ML: Platform-Based Design of Systems-on-Chip for Embedded Machine Learning, <a href="https://sld.cs.columbia.edu/pubs/giri_date20.pdf"> DATE Conference 2020 </a>. </li>
5865
<li> Accelerated Machine Learning as a Service for Particle Physics Computing, <a href="https://ml4physicalsciences.github.io/files/NeurIPS_ML4PS_2019_64.pdf">NeurIPS ML4PS Workshop 2019</a>. </li>
5966
<li> Low-latency machine learning inference on FPGAs, <a href="https://ml4physicalsciences.github.io/files/NeurIPS_ML4PS_2019_74.pdf">NeurIPS ML4PS Workshop 2019</a>. </li>
6067
<li> Fast inference of deep neural networks in FPGAs for particle physics, <a href="https://doi.org/10.1088/1748-0221/13/07/P07027">JINST 13, P07027 (2018)</a>. </li>
61-
<li> FPGA-accelerated machine learning inference as a service for particle physics computing, <a href="https://doi.org/10.1007/s41781-019-0027-2">Comput. Softw. Big Sci. 3, 13 (2019)</a> </li>
68+
<li> FPGA-accelerated machine learning inference as a service for particle physics computing, <a href="https://doi.org/10.1007/s41781-019-0027-2">Comput. Softw. Big Sci. 3, 13 (2019)</a>. </li>
6269
</ul>
6370
</p>
6471
<h3> Talks/Videos </h3>
6572
<p style="line-height:1.3">
6673
List of various presentations from the community<br>
6774
<ul>
68-
<li> P. Harris, ML Acceleration with Heterogeneous Computing for Big Data Physics Experiments, Heterogeneous High Performance Computing Workshop at Supercomputing 2019, <a href="https://h2rc.cse.sc.edu/slides/invited1_Harris.pdf">slides</a></li>
75+
<li> C. Herwig, An ML Control System for the Fermilab Booster, BIDS Machine Learning and Science Forum, April 2021, <a href="https://bids.berkeley.edu/events/machine-learning-and-science-forum-2021-0405">abstract</a></li>
76+
<li> P. Harris, Quick and Quirk with Quarks, IAIFI Colloquium Online, March 2021, <a href="https://www.youtube.com/watch?v=9_vNh09qqmw">video</a></li>
77+
<li> P. Harris, Scientific Applications of FPGAs at the LHC, ISFPGA 2021 (keynote), <a href="https://dl.acm.org/doi/10.1145/3431920.3437119">abstract</a></li>
78+
<li> J. Duarte, AI at the Edge of Particle Physics, <a href="https://argonne.zoomgov.com/rec/play/-Zjdo2cH5hq0gPOaG36RLVU_mTGUDjP_w3AuI0pajsw6WTpSiKhX0qLxGLW3gP4xNVkhnIBpv8ebNdw1.oOyAyU_bdLDggX_Q?continueMode=true">video</a></li>
79+
<li> J. Duarte, hls4ml: An open-source codesign workflow to empower scientific low-power machine learning devices, tinyML Research Symposium 2021, <a href="https://www.youtube.com/watch?v=9p7pRqise8I">video</a></li>
80+
<li> D. Rankin, FPGAs-as-a-Service Toolkit (FaaST), Heterogeneous High-Performance Reconfigurable Computing Workshop at Supercomputing 2020, <a href="https://h2rc.cse.sc.edu/2020/slides/08_Rankin.pdf">slides</a></li>
81+
<li> P. Harris, ML Acceleration with Heterogeneous Computing for Big Data Physics Experiments, Heterogeneous High-Performance Reconfigurable Computing Workshop at Supercomputing 2019, <a href="https://h2rc.cse.sc.edu/2019/slides/invited1_Harris.pdf">slides</a></li>
6982
<li> K. Pedro, FPGA-accelerated machine learning inference as a service for particle physics computing, CHEP 2019, <a href="https://indico.cern.ch/event/773049/contributions/3474731/">slides</a></li>
7083
<li> J. Duarte, Machine Learning on FPGAs for low latency and high throughput inference, eScience 2019, <a href="https://escience2019.sched.com/event/Uuiy/machine-learning-on-fpgas-for-low-latency-and-high-throughput-inference?iframe=yes&w=100%&sidebar=yes&bg=no#">slides</a></li>
7184
<li> M. Liu, FPGA-accelerated machine learning inference as a solution for particle physics computing challenges, PASC 2019, <a href="https://pasc19.pasc-conference.org/program/schedule/presentation/?id=msa134&sess=sess164">slides</a></li>

0 commit comments

Comments
 (0)