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)))
(One intermediate revision by the same user not shown)
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>
 +
<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>
 +
<div class="rw-ui-container rw-urid-731"></div>
 +
</body>
 +
</html>
 +
  
 
[[Category:General Articles]]
 
[[Category:General Articles]]

Revision as of 03:57, 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