<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>0035-001X</journal-id>
<journal-title><![CDATA[Revista mexicana de física]]></journal-title>
<abbrev-journal-title><![CDATA[Rev. mex. fis.]]></abbrev-journal-title>
<issn>0035-001X</issn>
<publisher>
<publisher-name><![CDATA[Sociedad Mexicana de Física]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0035-001X2007000100003</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Extended &#945;&#946; associative memories]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Sossa Azuela]]></surname>
<given-names><![CDATA[J.H]]></given-names>
</name>
<xref ref-type="aff" rid="A01"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Barrón Fernández]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<xref ref-type="aff" rid="A01"/>
</contrib>
</contrib-group>
<aff id="A01">
<institution><![CDATA[,Instituto Politécnico Nacional Centro de Investigación en Computación ]]></institution>
<addr-line><![CDATA[México D.F]]></addr-line>
<country>MÉXICO</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>02</month>
<year>2007</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>02</month>
<year>2007</year>
</pub-date>
<volume>53</volume>
<numero>1</numero>
<fpage>10</fpage>
<lpage>20</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S0035-001X2007000100003&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S0035-001X2007000100003&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S0035-001X2007000100003&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[The &#945;&#946; associative memories recently developed in Ref 10 have proven to be powerful tools for memorizing and recalling patterns when they appear distorted by noise. However they are only useful in the binary case. In this paper we show that it is possible to extend these memories now to the gray-level case. To get the desired extension, we take the original operators &#945; and &#946;, foundation of the &#945;&#946; memories, and propose a more general family of operators. We find that the original operators &#945; and &#946; are a subset of these extended operators. For this we first formulate a set of functional equations in terms of the original properties of operators &#945; and &#946;. Next we solve this system of equations and find a family of solutions. We show that the &#945; and &#946; originally proposed in Ref. 10 are just a particular case of this new family. We present the properties of the new operators. We then use these operators to build a new set of extended memories. We also give the conditions under which the extended memories are able to recall a pattern either from the pattern's fundamental set or from altered versions of them. We give real examples with images where the proposed memories show their efficiency. We compare the proposal with other similar works, and show the ours performs much better.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[Las memorias &#945;&#946; recientemente desarrolladas en Ref. 10 han mostrado ser herramientas poderosas para memorizar y recobrar patrones cuando éstos aparecen distorsionados por ruido. Sin embargo, son sólo útiles en el caso binario. En este artículo mostramos que es posible extender estas memorias para trabajar en el caso de niveles de gris. Para obtener esta extensión tomamos los operadores originales &#945; y &#946;, fundamento de las memorias &#945;&#946; y proponemos una familia más general, de la cual forman parte los originales. Para esto formulamos un conjunto de ecuaciones funcionales en términos de las propiedades de los operadores originales. Enseguida, resolvemos este sistema y encontramos una familia de soluciones. Mostramos que los operadores originales &#945; y &#946; son un caso particular de esta nueva familia. Damos algunas de las propiedades de los nuevos operadores. Usamos entonces los nuevos operadores para construir un conjunto de memorias extendidas. Damos las condiciones bajo las cuales estas memorias son capaces de recuperar patrones del conjunto fundamental o a partir de versiones ruidosas de las mismas. Damos también ejemplos reales con imágenes donde las memorias propuestas muestran su eficiencia. Comparamos la propuesta con otras propuestas similares y demostramos que la nuestra tiene un mucho mejor desempeño.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[Computer science and technology]]></kwd>
<kwd lng="en"><![CDATA[neural engineering]]></kwd>
<kwd lng="en"><![CDATA[image quality]]></kwd>
<kwd lng="en"><![CDATA[contrast]]></kwd>
<kwd lng="en"><![CDATA[resolution]]></kwd>
<kwd lng="en"><![CDATA[noise]]></kwd>
<kwd lng="es"><![CDATA[Ciencias de la computación y tecnología]]></kwd>
<kwd lng="es"><![CDATA[Ingeniería neuronal]]></kwd>
<kwd lng="es"><![CDATA[calidad de imagen]]></kwd>
<kwd lng="es"><![CDATA[contraste]]></kwd>
<kwd lng="es"><![CDATA[resolución]]></kwd>
<kwd lng="es"><![CDATA[ruido]]></kwd>
</kwd-group>
</article-meta>
</front><body><![CDATA[ <p align="justify"><font face="verdana" size="4">Investigaci&oacute;n</font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     <p align="center"><font face="verdana" size="4"><b>Extended <i>&alpha;&beta; </i>associative memories</b></font></p>     <p align="center"><font face="verdana" size="2">&nbsp;</font></p>     <p align="center"><font face="verdana" size="2"><b>J.H. Sossa Azuela* and R. Barr&oacute;n Fern&aacute;ndez</b></font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     <p align="justify"><i><font size="2" face="verdana">* Corresponding author.</font></i></p>     <p align="justify"><font face="verdana" size="2"><i>Centro de Investigaci&oacute;n en Computaci&oacute;n, Instituto Polit&eacute;cnico Nacional, </i><i>Av. Juan de Dios Bat&iacute;z and M. Oth&oacute;n de Mendiz&aacute;bal, Col. Nueva Industrial Vallejo, M&eacute;xico, D.F. 07738. M&Eacute;XICO, Tel. 5729 6000 ext, 56512. Fax 5729 6000 ext. 56607, e&#150;mail: <a href="mailto:hsossa@cic.ipn.mx">hsossa@cic.ipn.mx</a>, <a href="mailto:rbarron@cic.ipn.mx">rbarron@cic.ipn.mx</a></i></font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     <p align="justify"><font face="verdana" size="2">Recibido el 11 de septiembre de 2006    ]]></body>
<body><![CDATA[<br>   Aceptado el 22 de noviembre de 2006</font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     <p align="justify"><font face="verdana" size="2"><b>Abstract</b></font></p>     <p align="justify"><font face="verdana" size="2">The <i>&alpha;&beta;</i> associative memories recently developed in Ref 10 have proven to be powerful tools for memorizing and recalling patterns when they appear distorted by noise. However they are only useful in the binary case. In this paper we show that it is possible to extend these memories now to the gray&#150;level case. To get the desired extension, we take the original operators <i>&alpha;</i> and <i>&beta;</i>, foundation of the <i>&alpha;&beta;</i> memories, and propose a more general family of operators. We find that the original operators <i>&alpha;</i> and <i>&beta;</i> are a subset of these extended operators. For this we first formulate a set of functional equations in terms of the original properties of operators <i>&alpha;</i> and <i>&beta;</i>. Next we solve this system of equations and find a family of solutions. We show that the <i>&alpha;</i> and <i>&beta;</i> originally proposed in Ref. 10 are just a particular case of this new family. We present the properties of the new operators. We then use these operators to build a new set of extended memories. We also give the conditions under which the extended memories are able to recall a pattern either from the pattern's fundamental set or from altered versions of them. We give real examples with images where the proposed memories show their efficiency. We compare the proposal with other similar works, and show the ours performs much better.</font></p>     <p align="justify"><font face="verdana" size="2"><b>Keywords: </b>Computer science and technology; neural engineering; image quality; contrast; resolution; noise.</font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     <p align="justify"><font face="verdana" size="2"><b>Resumen</b></font></p>     <p align="justify"><font face="verdana" size="2">Las memorias <i>&alpha;&beta;</i> recientemente desarrolladas en Ref. 10 han mostrado ser herramientas poderosas para memorizar y recobrar patrones cuando &eacute;stos aparecen distorsionados por ruido. Sin embargo, son s&oacute;lo &uacute;tiles en el caso binario. En este art&iacute;culo mostramos que es posible extender estas memorias para trabajar en el caso de niveles de gris. Para obtener esta extensi&oacute;n tomamos los operadores originales <i>&alpha;</i> y<i> &beta;</i>, fundamento de las memorias <i>&alpha;&beta;</i> y proponemos una familia m&aacute;s general, de la cual forman parte los originales. Para esto formulamos un conjunto de ecuaciones funcionales en t&eacute;rminos de las propiedades de los operadores originales. Enseguida, resolvemos este sistema y encontramos una familia de soluciones. Mostramos que los operadores originales <i>&alpha;</i> y <i>&beta;</i> son un caso particular de esta nueva familia. Damos algunas de las propiedades de los nuevos operadores. Usamos entonces los nuevos operadores para construir un conjunto de memorias extendidas. Damos las condiciones bajo las cuales estas memorias son capaces de recuperar patrones del conjunto fundamental o a partir de versiones ruidosas de las mismas. Damos tambi&eacute;n ejemplos reales con im&aacute;genes donde las memorias propuestas muestran su eficiencia. Comparamos la propuesta con otras propuestas similares y demostramos que la nuestra tiene un mucho mejor desempe&ntilde;o.</font></p>     <p align="justify"><font face="verdana" size="2"><b>Descriptores: </b>Ciencias de la computaci&oacute;n y tecnolog&iacute;a; Ingenier&iacute;a neuronal; calidad de imagen; contraste; resoluci&oacute;n; ruido. </font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     ]]></body>
<body><![CDATA[<p align="justify"><font face="verdana" size="2">PACS: 89.20.Ff; 87.80.Xs; 87.57.Ce</font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     <p align="justify"><font face="verdana" size="2"><a href="/pdf/rmf/v53n1/v53n1a3.pdf">DESCARGAR ART&Iacute;CULO EN FORMATO PDF</a></font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     <p align="justify"><font face="verdana" size="2"><b>Acknowledgements</b></font></p>     <p align="justify"><font face="verdana" size="2">This work was economically supported by SIP&#150;IPN under grants 20050156, 20060517 and 20071438, and CONACYT by means of grant 46805.</font></p>     <p align="justify"><font face="verdana" size="2">&nbsp;</font></p>     <p align="justify"><font face="verdana" size="2"><b>References</b></font></p>     <!-- ref --><p align="justify"><font face="verdana" size="2">1. M.H. Hassoun, <i>Associative Neural Memories: Theory and Implementation </i>(Oxford University Press, 1993).</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330938&pid=S0035-001X200700010000300001&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">2. J.A. Anderson, <i>Mathematical Biosciences, </i><b>14</b> (1972) 197.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330939&pid=S0035-001X200700010000300002&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">3. J.A. Anderson and T. Kohonen (Eds.) <i>Neurocomputing: Foundations of Research </i>(Cambridge, MIT Press, 1990).</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330940&pid=S0035-001X200700010000300003&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">4. M.H. Hassoun, <i>Fundamentals of Artificial Neural Networks </i>(The MIT Press. 1995).</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330941&pid=S0035-001X200700010000300004&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">5. K. Steinbuch, <i>Kybernetik </i><b>1</b> (1961) 26.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330942&pid=S0035-001X200700010000300005&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">6. K. Steinbuch and H. Frank, <i>Kybernetik, </i><b>1</b> (1961) 117.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330943&pid=S0035-001X200700010000300006&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">7. J. J. Hopfield, <i>Proceedings of the National Academy of Sciences </i><b>79</b> (1982) 2554.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330944&pid=S0035-001X200700010000300007&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">8. G.X. Ritter, P. Sussner, and J.L. D&iacute;az de Le&oacute;n, <i>IEEE Transactions on Neural Networks </i><b>9</b> (1998) 281.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330945&pid=S0035-001X200700010000300008&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">9. G.X. Ritter, J.L. D&iacute;az de Le&oacute;n, and P. Sussner <i>Neural Networks </i><b>12</b> (1999) 851.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330946&pid=S0035-001X200700010000300009&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">10. C. Y&aacute;&ntilde;ez, Associative Memories based on Order Relations and Binary Operators (In Spanish), PhD Thesis, Center for Computing Research, February of 2002, (2002).</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330947&pid=S0035-001X200700010000300010&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">11. H. Sossa <i>et al., Lecture Notes on Computer Science </i><b>3287        </b>(2004) 187. </font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330948&pid=S0035-001X200700010000300011&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">12. H.  Sossa <i>et al., Lecture Notes on Computer Science </i><b>3287 </b>(2004) 195.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330949&pid=S0035-001X200700010000300012&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">13. H. Sossa <i>et al., Lecture Notes on Artificial Intelligence </i><b>3315 </b>(2004) 656.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330950&pid=S0035-001X200700010000300013&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">14. H. Sossa <i>et al., Lecture Notes on Artificial Intelligence </i><b>3315</b>&nbsp;(2004) 687.&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; </font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330951&pid=S0035-001X200700010000300014&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">15. H. Sossa <i>et al., Lecture Notes on Artificial Intelligence </i><b>3315</b>&nbsp;(2004) 646.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330952&pid=S0035-001X200700010000300015&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">16. H. Sossa <i>et al., Neural Processing Letters </i><b>22 </b>(2005) 85.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330953&pid=S0035-001X200700010000300016&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">17. R. A. V&aacute;zquez, H Sossa, and R. Barr&oacute;n, <i>LNAI</i> <b>3789</b> (2005) 317.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330954&pid=S0035-001X200700010000300017&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">18. H. Sossa and R. Barren, <i>Lecture Notes on Computer Science </i><b>3773 </b>(2005) 1036.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330955&pid=S0035-001X200700010000300018&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">19. R.A. Vazquez, H. Sossa, and B. Garro, <i>Lecture Notes on Artificial Intelligence </i><b>4293 </b>(2006) 367.</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330956&pid=S0035-001X200700010000300019&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">20. B. Cruz, H. Sossa, and R. Barr&oacute;n, to appear in <i>Neural Process<i>ing Letters </i></i>(2006)<i>.</i></font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330957&pid=S0035-001X200700010000300020&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">21. A. Dhombres, <i>Functional Equations Containing Several Variables </i>(Cambridge University Press, 1991)</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330958&pid=S0035-001X200700010000300021&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --><!-- ref --><p align="justify"><font face="verdana" size="2">22. J. Aczel, <i>Functional Equations: History, applications end the</i><i>ory </i>(Kluwer Academic Pub. Group, 1984).</font>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;[&#160;<a href="javascript:void(0);" onclick="javascript: window.open('/scielo.php?script=sci_nlinks&ref=8330959&pid=S0035-001X200700010000300022&lng=','','width=640,height=500,resizable=yes,scrollbars=1,menubar=yes,');">Links</a>&#160;]<!-- end-ref --> ]]></body><back>
<ref-list>
<ref id="B1">
<label>1</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[H. Hassoun]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<source><![CDATA[Associative Neural Memories: Theory and Implementation]]></source>
<year>1993</year>
<publisher-name><![CDATA[Oxford University Press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B2">
<label>2</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[A. Anderson]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<source><![CDATA[Mathematical Biosciences]]></source>
<year>1972</year>
<numero>14</numero>
<issue>14</issue>
<page-range>197</page-range></nlm-citation>
</ref>
<ref id="B3">
<label>3</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[A. Anderson]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Kohonen]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
</person-group>
<source><![CDATA[Neurocomputing: Foundations of Research]]></source>
<year>1990</year>
<publisher-loc><![CDATA[Cambridge ]]></publisher-loc>
<publisher-name><![CDATA[MIT Press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B4">
<label>4</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[H. Hassoun]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<source><![CDATA[Fundamentals of Artificial Neural Networks]]></source>
<year>1995</year>
<publisher-name><![CDATA[The MIT Press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B5">
<label>5</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Steinbuch]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
</person-group>
<source><![CDATA[Kybernetik]]></source>
<year>1961</year>
<numero>1</numero>
<issue>1</issue>
<page-range>26</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>6</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Steinbuch]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Frank]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<source><![CDATA[Kybernetik]]></source>
<year>1961</year>
<numero>1</numero>
<issue>1</issue>
<page-range>117</page-range></nlm-citation>
</ref>
<ref id="B7">
<label>7</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[J. Hopfield]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
<conf-name><![CDATA[79 Proceedings of the National Academy of Sciences]]></conf-name>
<conf-date>1982</conf-date>
<conf-loc> </conf-loc>
<page-range>2554</page-range></nlm-citation>
</ref>
<ref id="B8">
<label>8</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[X. Ritter]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Sussner]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Díaz de León]]></surname>
<given-names><![CDATA[J.L]]></given-names>
</name>
</person-group>
<source><![CDATA[]]></source>
<year></year>
<conf-name><![CDATA[9 IEEE Transactions on Neural Networks]]></conf-name>
<conf-date>1998</conf-date>
<conf-loc> </conf-loc>
<page-range>281</page-range></nlm-citation>
</ref>
<ref id="B9">
<label>9</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[X. Ritter]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Díaz de León]]></surname>
<given-names><![CDATA[J.L]]></given-names>
</name>
<name>
<surname><![CDATA[Sussner]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
</person-group>
<source><![CDATA[Neural Networks]]></source>
<year>1999</year>
<numero>12</numero>
<issue>12</issue>
<page-range>851</page-range></nlm-citation>
</ref>
<ref id="B10">
<label>10</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yáñez]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<source><![CDATA[Associative Memories based on Order Relations and Binary Operators (In Spanish)]]></source>
<year>Febr</year>
<month>ua</month>
<day>ry</day>
</nlm-citation>
</ref>
<ref id="B11">
<label>11</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<source><![CDATA[Lecture Notes on Computer Science]]></source>
<year>2004</year>
<numero>3287</numero>
<issue>3287</issue>
<page-range>187</page-range></nlm-citation>
</ref>
<ref id="B12">
<label>12</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<source><![CDATA[Lecture Notes on Computer Science]]></source>
<year>2004</year>
<numero>3287</numero>
<issue>3287</issue>
<page-range>195</page-range></nlm-citation>
</ref>
<ref id="B13">
<label>13</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<source><![CDATA[Lecture Notes on Artificial Intelligence]]></source>
<year>2004</year>
<numero>3315</numero>
<issue>3315</issue>
<page-range>656</page-range></nlm-citation>
</ref>
<ref id="B14">
<label>14</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<source><![CDATA[Lecture Notes on Artificial Intelligence]]></source>
<year>2004</year>
<numero>3315</numero>
<issue>3315</issue>
<page-range>687</page-range></nlm-citation>
</ref>
<ref id="B15">
<label>15</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<source><![CDATA[Lecture Notes on Artificial Intelligence]]></source>
<year>2004</year>
<numero>3315</numero>
<issue>3315</issue>
<page-range>646</page-range></nlm-citation>
</ref>
<ref id="B16">
<label>16</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
</person-group>
<source><![CDATA[Neural Processing Letters]]></source>
<year>2005</year>
<numero>22</numero>
<issue>22</issue>
<page-range>85</page-range></nlm-citation>
</ref>
<ref id="B17">
<label>17</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[A. Vázquez]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Barrón]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<source><![CDATA[LNAI]]></source>
<year>2005</year>
<numero>3789</numero>
<issue>3789</issue>
<page-range>317</page-range></nlm-citation>
</ref>
<ref id="B18">
<label>18</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Barren]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<source><![CDATA[Lecture Notes on Computer Science]]></source>
<year>2005</year>
<numero>3773</numero>
<issue>3773</issue>
<page-range>1036</page-range></nlm-citation>
</ref>
<ref id="B19">
<label>19</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[A. Vazquez]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Garro]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
</person-group>
<source><![CDATA[Lecture Notes on Artificial Intelligence]]></source>
<year>2006</year>
<numero>4293</numero>
<issue>4293</issue>
<page-range>367</page-range></nlm-citation>
</ref>
<ref id="B20">
<label>20</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cruz]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Sossa]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Barrón]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<source><![CDATA[to appear in Neural Processing Letters]]></source>
<year>2006</year>
</nlm-citation>
</ref>
<ref id="B21">
<label>21</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Dhombres]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<source><![CDATA[Functional Equations Containing Several Variables]]></source>
<year>1991</year>
<publisher-name><![CDATA[Cambridge University Press]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B22">
<label>22</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Aczel]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<source><![CDATA[Functional Equations: History, applications end theory]]></source>
<year>1984</year>
<publisher-name><![CDATA[Kluwer Academic Pub. Group]]></publisher-name>
</nlm-citation>
</ref>
</ref-list>
</back>
</article>
