# NNPDF > Mediated Wiki article. Canonical URL: https://mediated.wiki/source/NNPDF > Markdown URL: https://mediated.wiki/source/NNPDF.md > Source: https://en.wikipedia.org/wiki/NNPDF > Source revision: 1328903619 > License: Creative Commons Attribution-ShareAlike 4.0 International (https://creativecommons.org/licenses/by-sa/4.0/) Particle physics collaboration This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these messages) This article relies largely or entirely on a single source. Relevant discussion may be found on the talk page. Please help improve this article by introducing citations to additional sources. Find sources: "NNPDF" – news · newspapers · books · scholar · JSTOR (November 2024) This article may be confusing or unclear to readers. Please help clarify the article. There might be a discussion about this on the talk page. (November 2024) (Learn how and when to remove this message) (Learn how and when to remove this message) NNPDF Developer The NNPDF Collaboration Stable release 4.0 Type Particle physics Website nnpdf.mi.infn.it **NNPDF** is the acronym used to identify the [parton distribution functions](/source/Parton_distribution_functions) from the NNPDF Collaboration. [*[citation needed](https://en.wikipedia.org/wiki/Wikipedia:Citation_needed)*]NNPDF parton densities are extracted from global fits to data based on a combination of a [Monte Carlo method](/source/Monte_Carlo_method) for uncertainty estimation and the use of [neural networks](/source/Neural_networks) as basic interpolating functions.[1] ## Methodology The NNPDF Collaboration strategy is summarized in this diagram. The NNPDF approach can be divided into four main steps: - The generation of a large sample of Monte Carlo replicas of the original experimental data, in a way that central values, errors and correlations are reproduced with enough accuracy. - The training (minimization of the χ 2 {\displaystyle \chi ^{2}} ) of a set of PDFs parametrized by [neural networks](/source/Artificial_neural_network) on each of the above MC replicas of the data. PDFs are parametrized at the initial evolution scale Q 0 2 {\displaystyle Q_{0}^{2}} and then evolved to the experimental data scale Q 2 {\displaystyle Q^{2}} by means of the [DGLAP](/source/DGLAP) equations. Since the PDF parametrization is redundant, the minimization strategy is based in [genetic algorithms](/source/Genetic_algorithm) as well as gradient descent based minimizers. - The neural network training is stopped dynamically before entering into the overlearning regime, that is, so that the PDFs learn the physical laws which underlie experimental data without fitting simultaneously statistical noise. - Once the training of the MC replicas has been completed, a set of statistical estimators can be applied to the set of PDFs, in order to assess the statistical consistency of the results. For example, the stability with respect PDF parametrization can be explicitly verified. The set of N r e p {\displaystyle N_{rep}} PDF sets (trained neural networks) provides a representation of the underlying PDF probability density, from which any statistical estimator can be computed. ## Example The image below shows the [gluon](/source/Gluon) at small-x from [the NNPDF1.0 analysis](https://arxiv.org/abs/0808.1231), available through [the LHAPDF interface](http://projects.hepforge.org/lhapdf/) - The NNPDF1.0 gluon ## Releases The NNPDF releases are summarised in the following table: PDF set DIS data Drell-Yan data Jet data LHC data Independent param. of s {\displaystyle s} and s ¯ {\displaystyle {\bar {s}}} Heavy Quark masses NNLO NNPDF4.0 Yes Yes Yes Yes Yes Yes Yes NNPDF3.1 Yes Yes Yes Yes Yes Yes Yes NNPDF3.0 Yes Yes Yes Yes Yes Yes Yes NNPDF2.3 Yes Yes Yes Yes Yes Yes Yes NNPDF2.2 Yes Yes Yes Yes Yes Yes Yes NNPDF2.1 Yes Yes Yes No Yes Yes Yes NNPDF2.0 Yes Yes Yes No Yes No No NNPDF1.2 Yes No No No Yes No No NNPDF1.0 Yes No No No No No No All PDF sets are available through the LHAPDF interface and in the [NNPDF webpage](http://nnpdf.mi.infn.it/for-users/). ## References 1. **[^](#cite_ref-1)** Miao, Qinghai; Wang, Fei-Yue (2024). [*Artificial Intelligence for Science (AI4S): Frontiers and Perspectives Based on Parallel Intelligence*](https://books.google.com/books?id=sM4gEQAAQBAJ&dq=%22NNPDF%22+-wikipedia&pg=PA50). Springer Nature. p. 50. [ISBN](/source/ISBN_(identifier)) [978-3-031-67419-8](https://en.wikipedia.org/wiki/Special:BookSources/978-3-031-67419-8). ## External links - [The NNPDF Collaboration homepage](http://nnpdf.hepforge.org) - [Download NNPDF Parton Distribution sets](http://sophia.ecm.ub.es/nnpdf/nnpdf-driver.htm)[*[permanent dead link](https://en.wikipedia.org/wiki/Wikipedia:Link_rot)*] - [The NNPDF1.0 analysis](https://arxiv.org/abs/0808.1231) - [The NNPDF Non-Singlet analysis](https://arxiv.org/abs/hep-ph/0701127) - [NNPDF3.1 release](https://link.springer.com/article/10.1140%2Fepjc%2Fs10052-017-5199-5) - [NNPDF latest fitting code](https://link.springer.com/article/10.1140%2Fepjc%2Fs10052-019-7197-2) - [The LHAPDF interface](http://projects.hepforge.org/lhapdf/) Authority control databases: Academics zbMATH --- Adapted from the Wikipedia article [NNPDF](https://en.wikipedia.org/wiki/NNPDF) by Wikipedia contributors ([contributor history](https://en.wikipedia.org/wiki/NNPDF?action=history)). Available under [Creative Commons Attribution-ShareAlike 4.0 International](https://creativecommons.org/licenses/by-sa/4.0/). Changes may have been made.