Metraipolis › archive › dc_c865829e64de
Interpreting the predictions of neural network classification based on a Taylor Coefficient Analysis (TCA) — arXiv:2609.12801
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12801
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:02:55.911Z
- SHA-256 of the archived text
58c1c1517fdace830c8361fc750cc8d693d241dfd02e3b90bb4a7b4b72b4a650- Stable URL of this page
https://metraipolis.com/documento/dc_c865829e64de
How to cite
Interpreting the predictions of neural network classification based on a Taylor Coefficient Analysis (TCA) — arXiv:2609.12801 — arXiv (en), https://arxiv.org/abs/2609.12801 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c865829e64de (Metraipolis archive dc_c865829e64de, sha256 58c1c1517fdace830c8361fc750cc8d693d241dfd02e3b90bb4a7b4b72b4a650)
BibTeX
@misc{dcc865829e64de,
title = {Interpreting the predictions of neural network classification based on a Taylor Coefficient Analysis (TCA) — arXiv:2609.12801},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12801},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c865829e64de; sha256 58c1c1517fdace830c8361fc750cc8d693d241dfd02e3b90bb4a7b4b72b4a650},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12801. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce a rigid and comprehensive taxonomy and paradigm for characterizing the influence of the input feature space $X$ on the predictions $\hat{y}$ of a neural network (NN) used for event classification, based on a Taylor expansion of $\hat{y}$ in $X$. The complete process of introspection we refer to as Taylor Coefficient Analysis (TCA). Based on two simplistic example tasks, which can be easily understood and bencmarked, we illustrate the power of the TCA when it comes to revealing, what properties of $X$ have led to what value of $\hat{y}$, of a given NN model, building up intuition for the method. A more complex application is meant to represent $X$ of a typical classification task at a CERN LHC experiment. Based on this application, we play through the different levels of introspection that the TCA offers and discuss a number of practical aspects for a TCA application typical for the analysis of CERN LHC data. We conclude with a study to support the assumption that those properties of $X$ most relevant for tasks of the complexity typical for a CERN LHC experiment, are usually caught by a TCA up to the second order.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Data Analysis, Statistics and Probability (physics.data-an).
Pagina del lavoro: https://arxiv.org/abs/2609.12801 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T02:51:27.822Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).