dorsal/arxiv
View SchemaStudies of Stability and Robustness for Artificial Neural Networks and Boosted Decision Trees
| Authors | Hai-Jun Yang, Byron P. Roe, Ji Zhu |
|---|---|
| Categories | |
| ArXiv ID | physics/0610276 |
| URL | https://arxiv.org/abs/physics/0610276 |
| DOI | 10.1016/j.nima.2007.02.081 |
| Journal | Nucl. Instrum. & Meth. A 574 (2007) 342-349 |
Abstract
In this paper, we compare the performance, stability and robustness of Artificial Neural Networks (ANN) and Boosted Decision Trees (BDT) using MiniBooNE Monte Carlo samples. These methods attempt to classify events given a number of identification variables. The BDT algorithm has been discussed by us in previous publications. Testing is done in this paper by smearing and shifting the input variables of testing samples. Based on these studies, BDT has better particle identification performance than ANN. The degradation of the classifications obtained by shifting or smearing variables of testing results is smaller for BDT than for ANN.
{
"annotation_id": "cacb1096-65ee-4573-b5ac-151198424457",
"date_created": "2026-03-02T18:01:14.519000Z",
"date_modified": "2026-03-02T18:01:14.519000Z",
"file_hash": "b8c2d5295c488eeac09f2e381b82cba53813023f702d5f9fa5e2333e2d02374d",
"private": false,
"record": {
"abstract": "In this paper, we compare the performance, stability and robustness of\nArtificial Neural Networks (ANN) and Boosted Decision Trees (BDT) using\nMiniBooNE Monte Carlo samples. These methods attempt to classify events given a\nnumber of identification variables. The BDT algorithm has been discussed by us\nin previous publications. Testing is done in this paper by smearing and\nshifting the input variables of testing samples. Based on these studies, BDT\nhas better particle identification performance than ANN. The degradation of the\nclassifications obtained by shifting or smearing variables of testing results\nis smaller for BDT than for ANN.",
"arxiv_id": "physics/0610276",
"authors": [
"Hai-Jun Yang",
"Byron P. Roe",
"Ji Zhu"
],
"categories": [
"physics.data-an"
],
"doi": "10.1016/j.nima.2007.02.081",
"journal_ref": "Nucl. Instrum. \u0026 Meth. A 574 (2007) 342-349",
"title": "Studies of Stability and Robustness for Artificial Neural Networks and Boosted Decision Trees",
"url": "https://arxiv.org/abs/physics/0610276"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "d4279a64-91e6-4aee-ab8e-8093721c7573",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}