# FPGA-Accelerated Neural Network Inference for Ultra-Low-Latency Recalibration and Classification of Physics Objects at 40 MHz within CMS

- Institution: CERN
- Department: CERN openlab Summer Student Programme 2023
- Speaker: Diptarko Choudhury
- Year: 2023
- Language: English
- Subjects: Physics
- Source: [CERN](https://videos.cern.ch/record/3009604)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

In the realm of data processing and physics analysis at the Large Hadron Collider (LHC), there exists a notable advantage of deep learning-based algorithms over traditional physics-based counterparts. This study explores cutting-edge methodologies for the low latency neural network inference on Field Programmable Gate Array (FPGA) devices. Specifically, we concentrate on the recalibration and classification of physics objects at a demanding rate of 40 MHz within the CMS framework. The primary objective of this work is to develop an ultra-low-latency neural network model, strategically combining various techniques such as Quantization Aware Training, Knowledge Distillation, transfer learning, and Pruning schedules to achieve an exceptionally low latency without compromising the integral reconstruction performance..

0:00:00 Slide 1

0:00:15 Slide 2

0:00:30 Slide 3

0:00:45 Slide 4

0:01:00 Slide 5

0:01:15 Slide 6

0:01:30 Slide 7

0:01:45 Slide 8

0:01:59 Slide 9

0:02:14 Slide 10

0:02:29 Slide 11

0:02:44 Slide 12

0:02:59 Slide 13

0:03:14 Slide 14

0:03:29 Slide 15

0:03:43 Slide 16

0:03:58 Slide 17

0:04:13 Slide 18

0:04:28 Slide 19

0:04:43 Slide 20

0:04:58 Slide 21

0:05:13 Slide 22

0:05:28 Slide 23

0:05:42 Slide 24

0:05:57 Slide 25

0:06:12 Slide 26

0:06:27 Slide 27

0:06:42 Slide 28

0:06:57 Slide 29

0:07:12 Slide 30

## Lectures

1. [FPGA-Accelerated Neural Network Inference for Ultra-Low-Latency Recalibration and Classification of Physics Objects at 40 MHz within CMS](https://invisiblenetwork.ai/learn/cern/3009604/90fd8e289a1f), 8 min (CERN's player)