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

Hardware specs:

Tesla V100 GPU

Example noisy input:

Example correct 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

Epochs	Training loss	Validation loss	Training Time	Inference Time	Train/Val Loss Plot	Example Case
50	0.0034	0.0035	108	0.000165
100	0.0027	0.0026	222	0.000162

Examples

Noisy	Correct	MLP	CNN

Work Plan

create a histogram comparing how many points in the reconstructed image match points in the ground truth
create a histogram comparing how many points in reconstructed image are noise (are not in the original image)
try network (trained with one track) with new data set that contains more than one track, and provide example plots for presentation
create the efficiency and noise plots for the multi-track data sample reconstruction.
train network with multi-track data and evaluate performance on multi-track testing sample.
put on the web site architecture of the network and try with a little deeper architecture (4032->2016->1008->336 -> 224 -> 336 -> 1008 -> 2016 -> 4032)

Resources

https://userweb.jlab.org/~gavalian/Documents/NN_Vary_Width_Depth%20(Nguyen).pdf https://userweb.jlab.org/~gavalian/ML/2020/AutoEncoder/

CNF:ML Data Denoise

Contents

Problem

Goal