<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Following up on our previous study on applying hierarchical clustering algorithms to high energy particle physics, this paper explores the possibilities to use deep learning to generate models capable of processing the clusterization themselves. The technique chosen for training is reinforcement learning, that allows the system to evolve based on interactions between the model and the underlying graph. The result is a model, that by learning on a modest dataset of 10, 000 nodes during 70 epochs can reach 83, 77% precision for hierarchical and 86, 33% for high energy jet physics datasets in predicting the appropriate clusters.</p></abstract>

Following up on our previous study on applying hierarchical clustering algorithms to high energy particle physics, this paper explores the possibilities to use deep learning to generate models capable of processing the clusterization themselves. The technique chosen for training is reinforcement learning, that allows the system to evolve based on interactions between the model and the underlying graph. The result is a model, that by learning on a modest dataset of 10, 000 nodes during 70 epochs can reach 83, 77% precision for hierarchical and 86, 33% for high energy jet physics datasets in predicting the appropriate clusters.

Hierarchical clustering with deep Q-learning

Acta Universitatis Sapientiae, Informatica

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"Hierarchical clustering with deep Q-learning"}

Following up on our previous study on applying hierarchical clustering algorithms to high energy particle physics, this paper explores the possibilities to use...

Hierarchical clustering with deep Q-learning

Online veröffentlicht: 29. Aug. 2018

Seitenbereich: 86 - 109

Eingereicht: 05. Apr. 2018

DOI: https://doi.org/10.2478/ausi-2018-0006

Schlüsselwörter
jet, cluster algorithm, hierarchical clustering, deep q-learning, neural network, multi-core, keras, cntk, louvain

© 2018 Richárd Forster et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Hierarchical clustering with deep Q-learning

Online veröffentlicht: 29. Aug. 2018

Seitenbereich: 86 - 109

Eingereicht: 05. Apr. 2018

DOI: https://doi.org/10.2478/ausi-2018-0006

Schlüsselwörterjet, cluster algorithm, hierarchical clustering, deep q-learning, neural network, multi-core, keras, cntk, louvain

© 2018 Richárd Forster et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Schlüsselwörter
jet, cluster algorithm, hierarchical clustering, deep q-learning, neural network, multi-core, keras, cntk, louvain