BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Concepts of Machine Learning & Deep Learning
DTSTART;VALUE=DATE-TIME:20260710T091000Z
DTEND;VALUE=DATE-TIME:20260710T094000Z
DTSTAMP;VALUE=DATE-TIME:20260815T000001Z
UID:indico-contribution-215-1159@events.grnet.gr
DESCRIPTION:Speakers: Vasileios  Kochliaridis (AUTH)\nThis presentation in
 troduces concepts of Machine Learning and Deep Learning\, with a focus on 
 time-series forecasting. The talk explains how systems can learn patterns 
 from data and make predictions without relying on explicit programming. It
  then focuses on Deep Learning\, which can model complex relationships in 
 large datasets\, with a special emphasis on forecasting models for time-se
 ries data. The webinar covers modern deep learning methods\, including LST
 Ms\, GRUs\, Temporal Convolutional Networks and Transformers. Participants
  will gain a clear overview of how these models are used in real-world app
 lications such as finance and energy.\n\nhttps://events.grnet.gr/event/215
 /contributions/1159/
LOCATION:
URL:https://events.grnet.gr/event/215/contributions/1159/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Forecasting Renewable Energy Production Using Machine Learning
DTSTART;VALUE=DATE-TIME:20260710T094000Z
DTEND;VALUE=DATE-TIME:20260710T103000Z
DTSTAMP;VALUE=DATE-TIME:20260815T000001Z
UID:indico-contribution-215-1160@events.grnet.gr
DESCRIPTION:Speakers: Anestis  Ampatzidis (EY & AUTH)\nThis presentation f
 ocuses on a practical application of Machine Learning and Deep Learning in
  renewable energy forecasting. Through Day-Ahead forecasting of solar ener
 gy production\, the discussion covers the complete data pipeline\, detaili
 ng how meteorological and historical records are processed to train predic
 tive ML models. Particular emphasis is placed onDeep Learning approaches s
 uch as Neural Networks. Additionally\, the role of Aggregators (FOSE) in t
 he modern energy market is examined to emphasize the real-world value of a
 ccurate forecasting. Finally\, a first version of an intuitive User Interf
 ace\, currently under development to manage the entire application pipelin
 e\, is presented\, offering a complete end-to-end perspective from raw dat
 a to the final user experience. The presentation also includes a hands-on 
 demonstration\, showcasing how a pre-trained Deep Learning model is used t
 o perform inference and generate solar energy production forecasts.\n\nhtt
 ps://events.grnet.gr/event/215/contributions/1160/
LOCATION:
URL:https://events.grnet.gr/event/215/contributions/1160/
END:VEVENT
BEGIN:VEVENT
SUMMARY:Introduction & Objectives
DTSTART;VALUE=DATE-TIME:20260710T090000Z
DTEND;VALUE=DATE-TIME:20260710T091000Z
DTSTAMP;VALUE=DATE-TIME:20260815T000001Z
UID:indico-contribution-215-1158@events.grnet.gr
DESCRIPTION:Speakers: Ioannis  Vlahavas (AUTH)\nThe introductory presentat
 ion will briefly present the necessity of and possibilities for usingAI an
 d in particular ML for forecasting time series that are influenced by many
  parameters. It will also discuss the value of reliable forecasting by ren
 ewable energy providers for the Energy Exchange\, consumers and the enviro
 nment. Moreover it will highlight the importance of abundant and high qual
 ity data\, as well as the continuous improvement of a forecasting system w
 ill also be addressed.\n\nhttps://events.grnet.gr/event/215/contributions/
 1158/
LOCATION:
URL:https://events.grnet.gr/event/215/contributions/1158/
END:VEVENT
END:VCALENDAR