Symmetric discrete universal neural networks

Eric Goles, Martín Matamala

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Given the class of symmetric discrete weight neural networks with finite state set {0,1}, we prove that there exist iteration modes under these networks which allow to simulate in linear space arbitrary neural networks (non-necessarily symmetric). As a particular result we prove that an arbitrary symmetric neural network can be simulated by a symmetric one iterated sequentially, with some negative diagonal weights. Further, considering only the synchronous update we prove that symmetric neural networks with one refractory state are able to simulate arbitrary neural networks.

Original languageEnglish
Pages (from-to)405-416
Number of pages12
JournalTheoretical Computer Science
Issue number2
StatePublished - 20 Nov 1996
Externally publishedYes


Dive into the research topics of 'Symmetric discrete universal neural networks'. Together they form a unique fingerprint.

Cite this