Metraipolis › archive › dc_7ebf4800ea39

Compositional pattern-producing network — Wikipedia (en)

Source: Wikipedia (en)
Original: https://en.wikipedia.org/wiki/Compositional_pattern-producing_network
License (as archived): CC-BY-SA-4.0
Archived: 2026-10-07T18:26:40.587Z
SHA-256 of the archived text: 8ed166b22df9c7f9e04e98feba8dbb38207b692e25e74dce868541bc9017e87b
Stable URL of this page: https://metraipolis.com/documento/dc_7ebf4800ea39

How to cite

Compositional pattern-producing network — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Compositional_pattern-producing_network (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_7ebf4800ea39 (Metraipolis archive dc_7ebf4800ea39, sha256 8ed166b22df9c7f9e04e98feba8dbb38207b692e25e74dce868541bc9017e87b)

BibTeX

@misc{dc7ebf4800ea39,
  title = {Compositional pattern-producing network — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/Compositional_pattern-producing_network},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_7ebf4800ea39; sha256 8ed166b22df9c7f9e04e98feba8dbb38207b692e25e74dce868541bc9017e87b},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Compositional_pattern-producing_network. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Compositional pattern-producing networks (CPPNs) are a variation of artificial neural networks (ANNs) that have an architecture whose evolution is guided by genetic algorithms. While ANNs often contain only sigmoid functions and sometimes Gaussian functions, CPPNs can include both types of functions and many others. The choice of functions for the canonical set can be biased toward specific types of patterns and regularities. For example, periodic functions such as sine produce segmented patterns with repetitions, while symmetric functions such as Gaussian produce symmetric patterns. Linear functions can be employed to produce linear or fractal-like patterns. Thus, the architect of a CPPN-based genetic art system can bias the types of patterns it generates by deciding the set of canonical functions to include. Furthermore, unlike typical ANNs, CPPNs are applied across the entire space of possible inputs so that they can represent a complete image. Since they are compositions of functions, CPPNs in effect encode images at infinite resolution and can be sampled for a particular display at whatever resolution is optimal. CPPNs can be evolved through neuroevolution techniques such as neuroevolution of augmenting topologies (called CPPN-NEAT). CPPNs have been shown to be a very powerful encoding when evolving the following: Neural networks, via the HyperNEAT algorithm, 2D images, on "PicBreeder.org" Archived 2011-07-25 at the Wayback Machine, 3D objects, on "EndlessForms.com" Archived 2018-11-14 at the Wayback Machine, Robot morphologies Rigid Robots Soft Robots.

Tema degli esploratori: statistica e scienza dei dati (deposito sistematico; ricerca «artificial neural network»).
Fonte: Wikipedia in inglese, voce «Compositional pattern-producing network» — https://en.wikipedia.org/wiki/Compositional_pattern-producing_network
Wikidata Q5156806: «variation of artificial neural networks that have an architecture whose evolution is guided by genetic algorithms» (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q5156806
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Compositional_pattern-producing_network?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1359950948, consultata il 2026-10-07T17:55:07.239Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 287bde716aaca6770387db92f5e6dd729acab5ae2f9d4ea024ce219f555932f0