Difference between revisions of "Classification and Generation of Digital Marble Art: OR and Deep Learning"

From IFORS Developing Countries Online Resources
Jump to: navigation, search
m (Protected "Classification and Generation of Digital Marble Art: OR and Deep Learning" ([Edit=Allow only administrators] (indefinite) [Move=Allow only administrators] (indefinite)))
Line 20: Line 20:
  
 
- our results are partially answering recent open questions about GAN framework proposed by (Odena [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/2019/11/Willi-Meltem-Suryati-EBRU-North-Sumatra-November-2019.pdf
 
link to material: https://ifors.org/wp-content/uploads/2019/11/Willi-Meltem-Suryati-EBRU-North-Sumatra-November-2019.pdf
 +
 +
<html>
 +
<head>
 +
</head>
 +
<body>
 +
<!-- Add this element exactly where you want the Rating-Widget to appear -->
 +
<div class="rw-ui-container rw-urid-1"></div>
 +
 +
<!--
 +
    You can add more Rating-Widgets in your site,
 +
    just pick some new rating-widget-unique-id (must be positive integer).
 +
    For example (rating-widget-unique-id = 731):
 +
    <div class="rw-ui-container rw-urid-731"></div>
 +
-->
 +
 +
<!-- Add this javascript code immediately before the </body> tag -->
 +
<div class="rw-js-container">
 +
    <script type="text/javascript">
 +
        // Async Rating-Widget initialization.
 +
        function RW_Async_Init(){
 +
            RW.init({
 +
                uid: "12D3F85CF26CD5E7A24D3695D86F50A0",
 +
                huid: "127128",
 +
                options: {
 +
                    style: "oxygen"
 +
                }
 +
            });
 +
            RW.render();
 +
        }
 +
 +
        // Append Rating-Widget JavaScript library.
 +
        if (typeof(RW) == "undefined"){
 +
            (function(){
 +
                var rw = document.createElement("script"),
 +
                    d = new Date(), ck = "Y" + d.getFullYear() + "M" + d.getMonth() + "D" + d.getDate();
 +
                rw.type = "text/javascript"; rw.async = true;
 +
                rw.src = "http://js.rating-widget.com/external.min.js?ck=" + ck;
 +
                var s = document.getElementsByTagName("script")[0];
 +
                s.parentNode.insertBefore(rw, s);
 +
            })();
 +
        }
 +
 +
    </script>
 +
</div>
 +
</body>
 +
</html>
  
 
[[Category:General Articles]]
 
[[Category:General Articles]]

Revision as of 03:54, 11 November 2019

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/2019/11/Willi-Meltem-Suryati-EBRU-North-Sumatra-November-2019.pdf