# Reusing Neural Networks: Lessons learned and Suggestions for the future

- Institution: CERN
- Department: Workshops
- Speaker: Tomasz Procter
- Year: 2022
- Language: English
- Subjects: Physics
- Source: [CERN](https://videos.cern.ch/record/3016356)
- 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)

I present the lessons learned as re-interpreters trying to reuse analyses centred on neural networks in the RIVET framework, using two recent ATLAS analyses -- SUSY and Exotics searches -- as examples. I survey the possible ways that an analysis team can preserve and publicise their neural network for future use, and provide a detailed examination of the ONNX and lwtnn preservation tools, describing their advantages and disadvantages for both the original analysis team and re-interpreters. I also comment on how thinking about re-use from the beginning could change how analyses design and use neural networks; and what supplementary data becomes even more important for validation..

0:00:00 Slide 1

0:01:03 Slide 2

0:02:03 Slide 3

0:03:08 Slide 4

0:04:27 Slide 5

0:06:31 Slide 6

0:08:02 Slide 7

0:10:34 Slide 8

0:11:41 Slide 9

0:13:36 Slide 10

0:16:36 Slide 11

0:18:36 Slide 12

## Lectures

1. [Reusing Neural Networks: Lessons learned and Suggestions for the future](https://invisiblenetwork.ai/learn/cern/3016356/a9dea9d390cb), 23 min (CERN's player)