About
Machine learning is becoming ubiquitous across HEP. There is great potential to improve trigger and DAQ performances with it. However, the exploration of such techniques within the field in low latency/power FPGAs has just begun. We present HLS4ML, a user-friendly software, based on High-Level Synthesis (HLS), designed to deploy network architectures on FPGAs. As a case study, we use HLS4ML for boosted-jet tagging with deep networks at the LHC. We show how neural networks can be made fit the resources available on modern FPGAs, thanks to network pruning and quantization. We map out resource usage and latency versus network architectures, to identify the typical problem complexity that HLS4ML could deal with. We discuss possible applications in current and future HEP experiments. .
0:00:00 Slide 1
0:01:22 Slide 2
0:01:28 Slide 3
0:01:53 Slide 4
0:02:31 Slide 5
0:03:47 Slide 6
0:04:36 Slide 7
0:05:01 Slide 8
0:05:21 Slide 9
0:06:11 Slide 10
0:06:34 Slide 11
The talk
Credits and licence
- Institution
- CERN
- Department
- EP-IT Data science seminars
- Speaker
- Jennifer Ngadiuba
- Year
- 2018
- Language
- English
- Subjects
- Computer science
- Source
- CERN
- Licence
- CERN, as CERN states it. CERN's terms
- Attribution
- © CERN. CERN provides its audiovisual media free of charge for educational and informational use, credited to CERN; this lecture is shown in CERN's own player.
- Who can watch
- CERN gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed