CNF:ML Data Denoise: Difference between revisions
Jump to navigation
Jump to search
Pthomadakis (talk | contribs) |
Pthomadakis (talk | contribs) |
||
| Line 36: | Line 36: | ||
! Inference Time | ! Inference Time | ||
! Train/Val Loss Plot | ! Train/Val Loss Plot | ||
! Example Case | |||
|- | |- | ||
| 0.0034 | | 0.0034 | ||
| Line 42: | Line 43: | ||
| 0.000165 | | 0.000165 | ||
| [[File:cnn_ae_loss.png|480px]] | | [[File:cnn_ae_loss.png|480px]] | ||
| [[File:cnf_ml_cnn_denoised_track.png|480px]] | |||
|} | |} | ||
=== Comparison === | === Comparison === | ||
Revision as of 16:35, 2 November 2020
This page will be updated about the machine learning data de-noising effort.
Problem
Traditional tracking algorithms are computationally intensive, especially for high luminosity experiments with multi-track final states where all combinations of segments in drift chambers have to be considered for firing best track candidates. At high luminosity the number of random segments (unrelated to the tracks) are increasing and as a result the number of possible combinations also increases, making the whole process longer.
Goal
Use Deep Learning Autoencoders that are trained on noisy tracks to produce the original track without the noise.
Results
Example noisy input:
Multilayer Perceptrons
| Training loss | Validation loss | Training Time | Inference Time | Train/Val Loss Plot | Example Case |
|---|---|---|---|---|---|
| 0.0018 | 0.0219 | 298 | 0.000182 | 
|
|
Convolutional Networks
| Training loss | Validation loss | Training Time | Inference Time | Train/Val Loss Plot | Example Case |
|---|---|---|---|---|---|
| 0.0034 | 0.0035 | 108 | 0.000165 | 
|
|