<div class="csl-bib-body">
<div class="csl-entry">Iglesias Vazquez, F. (2024, March 13). <i>Clustering and Anomaly Detection: Deep or Shallow Learning?</i> [Presentation]. Universitat Politecnica de Catalunya UPC Conference/Seminar, Barcelona, Spain.</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/195710
-
dc.description.abstract
In numerous classification applications, deep learning has achieved accuracy levels that were unimaginable just a few years ago. However, within the two primary branches of unsupervised learning —clustering and anomaly detection— the advantages of deep learning over traditional options are commonly uncertain or even non-existent. Why is this the case? Is unsupervised deep learning inadvisable when compared to shallow learning? Are they alternative or complementary approaches? In this talk, we aim to address these questions by delving into the characteristics and requirements of unsupervised learning, contrasting them with the limitations of deep learning and its current capabilities for these types of tasks.
Whether for describing, modeling, or predicting the behavior of any phenomenon captured in the form of data, unsupervised learning (whether as a central component or as a support) is indispensable in data analysis. It is a key element in the next AI, given the necessity for adaptive systems capable of facing novelty and the unknown.
en
dc.language.iso
en
-
dc.subject
clustering
en
dc.subject
anomaly detection
en
dc.subject
deep learning
en
dc.subject
shallow learning
en
dc.title
Clustering and Anomaly Detection: Deep or Shallow Learning?
en
dc.type
Presentation
en
dc.type
Vortrag
de
dc.type.category
Presentation
-
tuw.publication.invited
invited
-
tuw.researchTopic.id
I1
-
tuw.researchTopic.id
C4
-
tuw.researchTopic.name
Logic and Computation
-
tuw.researchTopic.name
Mathematical and Algorithmic Foundations
-
tuw.researchTopic.value
50
-
tuw.researchTopic.value
50
-
tuw.publication.orgunit
E389 - Institute of Telecommunications
-
tuw.author.orcid
0000-0001-6081-969X
-
tuw.event.name
Universitat Politecnica de Catalunya UPC Conference/Seminar
en
tuw.event.startdate
13-03-2024
-
tuw.event.enddate
13-03-2024
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Barcelona
-
tuw.event.country
ES
-
tuw.event.institution
Universidad Politécnica de Cataluña - Barcelona Tech - UPC