<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body dir="ltr">
<div class="moz-forward-container">
<div class="moz-forward-container">
<div class="moz-forward-container">
<div lang="EN-US" link="blue" vlink="purple"
style="word-wrap:break-word">
<div>
<div class="x_WordSection1">
<div>
<p class="v1v1msonormal"><span
style="font-size:11.0pt">Dear AI scientists and
students,<span style="color:black"></span></span></p>
</div>
<div style="margin-top:12.0pt; margin-bottom:12.0pt">
<p class="x_MsoNormal" style="line-height:15.0pt"><span
style="font-size:11.0pt">University of Connecticut
hosts the <span style="color:black">attached
upcoming exciting lecture by Dr. Ioannis Pitas <i>Chair
of the International AI Doctoral Academy (</i></span><a
href="https://www.i-aida.org/"
originalsrc="https://www.i-aida.org/"
target="_blank" moz-do-not-send="true"><i>AIDA</i></a><i><span
style="color:black">) Principal Researcher at
Aristotle University of Thessaloniki (AUTH)
and CERTH/ITI Greece.</span></i> You are
welcomed to attend.</span></p>
</div>
<div style="margin-top:12.0pt; margin-bottom:12.0pt">
<p class="x_MsoNormal" style="line-height:15.0pt"><span
style="font-size:11.0pt; color:black">When &
Where: June 11th, 2026 @ 12:00pm </span><span
style="font-size:11.0pt">EDT, <span
style="color:black">IPB Room 203</span>,
University of Connecticut, Storrs, CT, USA<span
style="color:black"></span></span></p>
</div>
<div style="margin-top:12.0pt; margin-bottom:12.0pt">
<p class="x_MsoNormal" style="line-height:15.0pt"><span
style="font-size:11.0pt; color:black">Virtual Zoom
link: </span><span
style="font-size:11.0pt; color:#1264A3"><a
href="https://authgr.zoom.us/j/92451144378"
originalsrc="https://authgr.zoom.us/j/92451144378"
moz-do-not-send="true"
class="moz-txt-link-freetext">https://authgr.zoom.us/j/92451144378</a></span><span
style="font-size:11.0pt"></span></p>
</div>
<div style="margin-top:12.0pt; margin-bottom:12.0pt">
<p class="x_MsoNormal" style="line-height:15.0pt"><span
style="font-size:11.0pt; color:#1264A3"> </span></p>
</div>
<div style="margin-top:12.0pt; margin-bottom:12.0pt">
<p class="x_MsoNormal" style="line-height:15.0pt"><b><span
style="font-size:11.0pt; color:black">Decentralized
Machine Learning for Natural Disaster Management
Applications</span></b><span
style="font-size:11.0pt; color:black"></span></p>
</div>
<div style="margin-top:12.0pt; margin-bottom:12.0pt">
<p class="x_MsoNormal" style="line-height:15.0pt"><b><span
style="font-size:11.0pt; color:black">Abstract:</span></b><span
style="font-size:11.0pt; color:black"></span></p>
</div>
<div style="margin-top:12.0pt; margin-bottom:12.0pt">
<p class="x_MsoNormal" style="line-height:15.0pt"><span
style="font-size:11.0pt; color:black">This lecture
overviews decentralized and distributed DNN
architectures and their implementation in
cloud/edge environments. Big data analysis can be
greatly facilitated if decentralized/distributed
DNN architectures are employed that interact with
each other for DNN training and/or inference using
the human Teacher-Student education paradigm. A
novel Learning-by-Education Node Community (LENC)
framework is presented that facilitates
communication and knowledge exchange among diverse
Deep Neural Networks (DNN) agents, undertaking the
role of a student or teacher DNN by offering or
absorbing knowledge respectively. The framework
enables efficient and effective knowledge transfer
among participating DNN agents while enhancing
their learning capabilities and fostering their
collaboration among diverse networks. The proposed
framework addresses the challenges of handling
diverse training data distributions and the
limitations of individual DNN agent learning
abilities. The LENC framework ensures the
exploitation of the best available teacher
knowledge upon learning a new task and protects
the DNN agents from catastrophic forgetting. The
experiments demonstrate the LENC framework
functionalities on multiple teacher-student
learning techniques and their integration with
lifelong learning. Our experiments manifest the
LEMA framework’s ability to maximize the accuracy
of all participating DNN agents in classification
tasks by leveraging the collaborative knowledge of
the framework. A LENC framework implementation in
cloud/edge environments is also overviewed.</span></p>
</div>
<div style="margin-top:12.0pt; margin-bottom:12.0pt">
<p class="x_MsoNormal" style="line-height:15.0pt"><span
style="font-size:11.0pt; color:black">Applications
are presented in big visual data analysis tasks
for Natural Disaster Management (NDM), focusing on
flood and wildfire monitoring, combatting and
management. As many players enter into NDM, from
first responders to civil authorities, NDM needs
big data analysis that is typically decentralized
and DDN-based and resides in the entire
edge-to-cloud computing continuum.</span></p>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</body>
</html>