Classification and Generation of Digital Marble Art: OR and Deep Learning

From IFORS Developing Countries Online Resources
Jump to: navigation, search

by: Gerhard Wilhelm Weber, Meltem Atay & Suryati Sitepu

OR and Art

- Generative adversarial networks (GANs) are types of neural networks which can be used to generate new data.

- they can be used to generate art pieces.

- We developed a new GAN framework specific to generate digital abstract art,

- we are introducing an open digital dataset for further research and collaboration opportunities.

Novelty

- This idea is based on merging certain Support Vector Machines (SVMs) (invented by Drucker et al. [1997]) with convolution operation of Convolutional Neural Networks (CNNs) (proposed by LeCun et al. [1995]),

- kernels widely used for SVMs are linear, nonlinear and radial basis function (RBF) kernel methods tested for CNNs,

- we are proposing a general model which would be able to generate visually attractive art pieces without human supervision using OR methodology (Sack [2019]),

- our results are partially answering recent open questions about GAN framework proposed by (Odena [2019]).


link to material: https://ifors.org/wp-content/uploads/2019/12/Willi-Meltem-Suryati-EBRU-North-Sumatra-November-2019_updated.pdf

<html> <head> </head> <body> <script type="text/javascript">(function(d, t, e, m){ 

   // Async Rating-Widget initialization.
   window.RW_Async_Init = function(){
       RW.init({
           huid: "141148",
           uid: "6db8b62d52afa816e07e3917b2d0ce28",
           source: "website",
           options: {
               "advanced": {
                   "layout": {
                       "lineHeight": "22px"
                   }
               },
               "size": "medium",
               "style": "oxygen"
           } 
       });
       RW.render();
   };

   // Append Rating-Widget JavaScript library.
   var rw, s = d.getElementsByTagName(e)[0], id = "rw-js",
       p = d.location.protocol, a = ("https:" == p ? "secure." + 
       m + "js/" : "js." + m), ck = "Y" + t.getFullYear() + "M" + 
       t.getMonth() + "D" + t.getDate();
   if (d.getElementById(id)) return;              
   rw = d.createElement(e);
   rw.id = id; rw.async = true; rw.type = "text/javascript";
   rw.src = p + "//" + a + "external.min.js?ck=" + ck;
   s.parentNode.insertBefore(rw, s);

}(document, new Date(), "script", "rating-widget.com/"));</script>

</body> </html>

Retrieved from "https://ifors.org/developing_countries/index.php?title=Classification_and_Generation_of_Digital_Marble_Art:_OR_and_Deep_Learning&oldid=1666"