Browsing by Author "Pérez, Jorge"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Attention is Turing complete
    (2021) Pérez, Jorge; Barceló Baeza, Pablo; Marinkovic, Javier
    Alternatives to recurrent neural networks, in particular, architectures based on self-attention, are gaining momentum for processing input sequences. In spite of their relevance, the computational properties of such networks have not yet been fully explored. We study the computational power of the Transformer, one of the most paradigmatic architectures exemplifying self-attention. We show that the Transformer with hard-attention is Turing complete exclusively based on their capacity to compute and access internal dense representations of the data. Our study also reveals some minimal sets of elements needed to obtain this completeness result.
  • Thumbnail Image
    Item
    Data Exchange Beyond Complete Data
    (2013) Arenas Saavedra, Marcelo Alejandro; Pérez, Jorge; Reutter de la Maza, Juan
  • Thumbnail Image
    Item
    Evolución de la textura de bayas de uva del cv. Thompson seedless = Evolution of the texture in Thompson Seedless Berries.
    (2000) Vargas, Alfredo; Pérez, Jorge; Zoffoli, Juan Pablo; Pérez, Alonso
  • No Thumbnail Available
    Item
    Some Remarks on the Paper "semQA: SPARQL with Idempotent Disjunction”
    (IEEE, 2011) Arenas Saavedra, Marcelo Alejandro; Gutiérrez Gallardo, Claudio; Pérez, Jorge
    In the paper, “semQA: SPARQL with Idempotent Disjunction”, the authors study the RDF query language SPARQL. In particular, they claim that some of the results presented in are not correct. In this note, we refute the claims made in, and actually show that some of the formal results of are incorrect.