BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//london2023.pydata.org//9WFUH3
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:STANDARD
DTSTART:20001029T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T010000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-cfp-9WFUH3@london2023.pydata.org
DTSTART;TZID=Europe/London:20230603T163000
DTEND;TZID=Europe/London:20230603T171000
DESCRIPTION:AutoEncoders (AEs) are among the most popular techniques in mod
 ern machine learning. Thanks to their strong representation learning capab
 ility\, they can be used not only to generate data\, but also for many oth
 er tasks\, e.g. clustering\, dimensionality reduction and transfer learnin
 g. \n\nDespite their popularity\, their application is usually advertised 
 mostly for applications with static tabular (e.g. for recommender systems)
  and image data (e.g. for computer vision tasks). With this talk we will t
 ry to shed some light on a less well-known area of application\, namely th
 e use of AEs with time series data. After a brief introduction on AEs we w
 ill highlight challenges to their application in the time-series domain wi
 th a particular focus on clustering\, features extraction and transfer lea
 rning. \n\nThe talk is for everyone with an interest in deep learning\, ti
 me series and their intersection. Despite some working knowledge of applie
 d machine learning (deep learning in particular) and time series analysis 
 would be beneficial\, the talk will be delivered in a format accessible to
  all data science practitioners.
DTSTAMP:20250709T215941Z
LOCATION:Warwick
SUMMARY:Autoencoders for Time Series Clustering - vincenzo crescimanna\, Va
 lerio Bonometti
URL:https://london2023.pydata.org/cfp/talk/9WFUH3/
END:VEVENT
END:VCALENDAR