BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Singapore
BEGIN:DAYLIGHT
DTSTART:20380119T111407
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
RRULE:FREQ=YEARLY;BYDAY=3TU;BYMONTH=1
TZNAME:+08
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19820101T000000
TZOFFSETFROM:+0730
TZOFFSETTO:+0800
RRULE:FREQ=YEARLY;BYDAY=1FR;BYMONTH=1
TZNAME:+08
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261112T220334Z
UID:86926528-6DC2-486F-BBD0-70A081631F64
DTSTART;TZID=Asia/Singapore:20261111T140000
DTEND;TZID=Asia/Singapore:20261111T163000
DESCRIPTION:Modern scientific discovery increasingly relies on computationa
 l methods that can explore complex search spaces\, identify hidden structu
 res in data\, and learn meaningful representations from large and heteroge
 neous datasets. This tutorial talk will discuss ways of addressing these t
 asks from the perspectives of multiobjective optimization\, clustering\, a
 nd artificial intelligence. This talk will present the fundamental concept
 s\, algorithms\, and emerging connections among these three areas\, with a
 n emphasis on their role in intelligent discovery.\n\nThe tutorial will be
 gin with the principles of multiobjective optimization\, including conflic
 ting objectives\, Pareto dominance\, Pareto-optimal solutions\, and trade-
 off analysis. Two influential evolutionary approaches\, the Non-dominated 
 Sorting Genetic Algorithm II (NSGA-II) and the Archived MultiobjectiveSimu
 lated Annealing (AMOSA) algorithm\, will be introduced to illustrate popul
 ation-based and simulated-annealing-based strategies for exploring multiob
 jective search spaces. An application to rational drug design will be brie
 fly demonstrated.\n\nThe second part will introduce clustering as an unsup
 ervised learning paradigm for discovering structure in unlabeled data. Fun
 damental methods\, including K-means and Fuzzy C-means (FCM)\, will be exp
 lained\, highlighting their assumptions\, optimization principles\, streng
 ths\, and limitations. Building on these foundations\, the tutorial will e
 xamine multiobjective optimization for clustering\, where competing criter
 ia such as cluster compactness and separation can be optimized simultaneou
 sly. An innovative technique for providing a single comprehensive clusteri
 ng of the data utilizing a novel combination of the multiple Pareto-optima
 l solutions in a supervised framework will be discussed. An application to
  clustering gene expression data will be briefly demonstrated.\n\nThe fina
 l part will connect these classical computational intelligence techniques 
 with modern AI. Topics will include some historical facts about the evolut
 ion from traditional machine learning to deep learning\, representation le
 arning\, attention mechanisms\, and Transformer architecture. Selected con
 temporary trends\, including foundation models\, generative AI\, retrieval
 -augmented generation\, and AI-assisted scientific discovery\, will be bri
 efly mentioned alongside their opportunities and limitations.\n\nIt is exp
 ected that on conclusion of the tutorial\, the participants will have a fa
 ir grasp of metaheuristics for multiobjective optimization\, a couple of w
 idely used clustering algorithms\, a technique for multiobjectiveclusterin
 g\, and the transformer model and some of its developments.\n\nEngineering
  Auditorium\, Block EA\, National University of Singapore\, Singapore\, Si
 ngapore\, Singapore
LOCATION:Engineering Auditorium\, Block EA\, National University of Singapo
 re\, Singapore\, Singapore\, Singapore
ORGANIZER:dipti@nus.edu.sg
SEQUENCE:10
SUMMARY:Multiobjective Optimization\, Clustering and AI: Towards Intelligen
 t Discovery
URL;VALUE=URI:https://events.vtools.ieee.org/m/591505
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;zfr3Q CDt4Ke &quot; dir=&quot;ltr&quot;&gt;&lt;span clas
 s=&quot;C9DxTc &quot;&gt;Modern scientific discovery increasingly relies on computation
 al methods that can explore complex search spaces\, identify hidden struct
 ures in data\, and learn meaningful representations from large and heterog
 eneous datasets. This tutorial talk will discuss ways of addressing these 
 tasks from the perspectives of multiobjective optimization\, clustering\, 
 and artificial intelligence. This talk will present the fundamental concep
 ts\, algorithms\, and emerging connections among these three areas\, with 
 an emphasis on their role in intelligent discovery.&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;
 zfr3Q CDt4Ke &quot; dir=&quot;ltr&quot;&gt;&lt;span class=&quot;C9DxTc &quot;&gt;The tutorial will begin wit
 h the principles of multiobjective optimization\, including conflicting ob
 jectives\, Pareto dominance\, Pareto-optimal solutions\, and trade-off ana
 lysis. Two influential evolutionary approaches\, the Non-dominated Sorting
  Genetic Algorithm II (NSGA-II) and the Archived MultiobjectiveSimulated A
 nnealing (AMOSA) algorithm\, will be introduced to illustrate population-b
 ased and simulated-annealing-based strategies for exploring multiobjective
  search spaces. An application to rational drug design will be briefly dem
 onstrated.&amp;nbsp\;&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;zfr3Q CDt4Ke &quot; dir=&quot;ltr&quot;&gt;&lt;span cla
 ss=&quot;C9DxTc &quot;&gt;The second part will introduce clustering as an unsupervised 
 learning paradigm for discovering structure in unlabeled data. Fundamental
  methods\, including K-means and Fuzzy C-means (FCM)\, will be explained\,
  highlighting their assumptions\, optimization principles\, strengths\, an
 d limitations. Building on these foundations\, the tutorial will examine m
 ultiobjective optimization for clustering\, where competing criteria such 
 as cluster compactness and separation can be optimized simultaneously. An 
 innovative technique for providing a single comprehensive clustering of th
 e data utilizing a novel combination of the multiple Pareto-optimal soluti
 ons in a supervised framework will be discussed. An application to cluster
 ing gene expression data will be briefly demonstrated.&lt;/span&gt;&lt;/p&gt;\n&lt;p clas
 s=&quot;zfr3Q CDt4Ke &quot; dir=&quot;ltr&quot;&gt;&lt;span class=&quot;C9DxTc &quot;&gt;The final part will conn
 ect these classical computational intelligence techniques with modern AI. 
 Topics will include some historical facts about the evolution from traditi
 onal machine learning to deep learning\, representation learning\, attenti
 on mechanisms\, and Transformer architecture. Selected contemporary trends
 \, including foundation models\, generative AI\, retrieval-augmented gener
 ation\, and AI-assisted scientific discovery\, will be briefly mentioned a
 longside their opportunities and limitations.&lt;/span&gt;&lt;/p&gt;\n&lt;p class=&quot;zfr3Q 
 CDt4Ke &quot; dir=&quot;ltr&quot;&gt;&lt;span class=&quot;C9DxTc &quot;&gt;It is expected that on conclusion
  of the tutorial\, the participants will have a fair grasp of metaheuristi
 cs for multiobjective optimization\, a couple of widely used clustering al
 gorithms\, a technique for multiobjectiveclustering\, and the transformer 
 model and some of its developments.&lt;/span&gt;&lt;span class=&quot;C9DxTc &quot;&gt;&amp;nbsp\;&lt;/s
 pan&gt;&lt;/p&gt;
END:VEVENT
END:VCALENDAR

