Skip to content

Commit

Permalink
Merge pull request #4 from jtimko16/improve-design
Browse files Browse the repository at this point in the history 
Add - added content, improved little bit formatting
  • Loading branch information
@jtimko16
jtimko16 authored Feb 28, 2024
2 parents 358d47a + 53ac2d8 commit bbc31e2
Showing 1 changed file with 56 additions and 14 deletions.
70 changes: 56 additions & 14 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -58,35 +58,44 @@
.pc-members {
margin-top: 20px;
}
.organizers-section {
background-color: #f9f9f9;
padding: 20px;
margin-top: 20px;
border-radius: 8px;
}

</style>
</head>
<body>

<header>
<h1>Workshop on Automated Machine Learning (AutoML)</h1>
<h1>Workshop on Automated Machine Learning (AutoML) - ECAI 2024</h1>
</header>

<section>
<main>
<!-- Your existing content remains unchanged -->

<!-- Workshop description -->
<div class="workshop-description">
<h2>Workshop Description:</h2>
<p>
As the demand for machine learning applications surges, it becomes evident that the available pool of knowledgeable data scientists cannot
scale proportionally with the increasing data volumes and diverse application requirements in our digital world. To address this challenge,
various automated machine learning (AutoML) frameworks have emerged, aiming to bridge the gap in human expertise by automating the construction
of machine learning pipelines. AutoML research aims to automate the machine learning process progressively, with the objective of making effective
methods accessible to everyone. Therefore, the workshop is designed for a diverse audience, including core machine learning researchers involved
in various ML domains related to AutoML, such as neural architecture search, hyperparameter optimization, meta-learning, and explainability
within the AutoML context. It also caters to domain experts seeking to apply machine learning to novel problem domains.
scale proportionally with the increasing data volumes and diverse application requirements in our digital world. To address this challenge,
various automated machine learning (AutoML) frameworks have emerged, aiming to bridge the gap in human expertise by automating the construction
of machine learning pipelines. AutoML research aims to automate the machine learning process progressively, with the objective of making effective
methods accessible to everyone. Therefore, the workshop is designed for a diverse audience, including core machine learning researchers involved
in various ML domains related to AutoML, such as neural architecture search, hyperparameter optimization, meta-learning, and explainability
within the AutoML context. It also caters to domain experts seeking to apply machine learning to novel problem domains.


</p>


<p>&nbsp;</p>
</p>
We invite submissions on the topics of:

<b>We invite submissions on the topics of:</b>
<ul>
<li>Model selection, hyper-parameter optimization, and model search</li>
<li>Neural architecture search</li>
Expand All @@ -108,9 +117,20 @@ <h2>Workshop Description:</h2>
<li>Hyperparameter agnostic algorithms</li>
<li>AutoML for neuro-fuzzy systems</li>
</ul>



<p>&nbsp;</p>

<b>Submissions:</b>

<p>
As workshop organizers, you will need to organize your own paper submission process, and ECAI cannot directly support you in that or cover any costs.
However, there are a number of free tools available. Specifically, you are welcome to try a new tool (https://chairingtool.com) currently under development
for IJCAI, which as the organizer of an ECAI workshop you can use free of charge and with premium support.
</p>
<!-- Format section -->
<h2>Format:</h2>

<b>Format:</b>
<p>
The workshop will follow the classical format of presentations of peer-reviewed papers followed by
discussion. The typical duration for the workshop is a full day. We will arrange invited talks
Expand All @@ -119,7 +139,7 @@ <h2>Format:</h2>
</p>

<!-- Attendance section -->
<h2>Attendance:</h2>
<b>Attendance:</b>
<p>
The workshop is timely and relevant for the data management and machine learning research
communities due to the rapid growth in machine learning applications in almost every application
Expand All @@ -130,7 +150,7 @@ <h2>Attendance:</h2>
</div>
<!-- List of potential workshop PC members -->
<div class="pc-members">
<h2>List of Potential Workshop PC Members:</h2>
<h3>List of Potential Workshop Participating Members:</h3>
<ul>
<li>Amin Beheshti, Professor, School of Computing, Macquarie University, Sydney, Australia</li>
<li>Riccardo Tommasini, Associate Professor at the Institute National des Sciences Appliquées (INSA)</li>
Expand All @@ -140,6 +160,28 @@ <h2>List of Potential Workshop PC Members:</h2>
<!-- Add more PC members as needed -->
</ul>
</div>


<div class="organizers-section">
<h2>Names, affiliations, and contact details of all workshop organisers:</h2>
<ul>
<li>
Prof. Jerry Chun-Wei Lin<br>
Faculty of Automatic Control, Electronics and Computer Science, Department of Distributed Systems and IT Devices, Silesian University of Technology, Poland<br>
<a href="mailto:[email protected]">[email protected]</a>
</li>
<li>
Assoc Prof. Radwa Elshawi<br>
Institute of Computer Science, Tartu University<br>
<a href="mailto:[email protected]">[email protected]</a>
</li>
<li>
Assoc Prof Stefania Tomasiello<br>
Department of Industrial Engineering, Università degli Studi di Salerno<br>
<a href="mailto:[email protected]">[email protected]</a>
</li>
</ul>
</div>
</main>


Expand Down

0 comments on commit bbc31e2

Please sign in to comment.