BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Tagging Anglo-Saxon Stone Sculptures Using Multi-Label Image Class
 ification ML Techniques  - Zeynep Aki - RSE\, University of Durham
DTSTART:20240425T120000Z
DTEND:20240425T130000Z
UID:TALK212881@talks.cam.ac.uk
CONTACT:Jack Atkinson
DESCRIPTION:This project involves developing a machine learning model to a
 utomatically classify images of Anglo Saxon Stone Sculptures based on thei
 r features\, referred to as "tags". The aim is to have a model that can ac
 curately identify various characteristics from these sculptures\, such as 
 animals\, patterns\, and architectural details\, in images it has not seen
  before.\n\nThe process begins with data preparation\, where images and as
 sociated metadata are standardized to ensure uniformity and relevance. Thi
 s step involves converting images to a common format\, organizing them sys
 tematically\, and refining the metadata to align with the model's needs. T
 his preparation is crucial as it directly impacts the model's ability to l
 earn and generalize from the training data.\n\nFollowing data preparation\
 , the project employs Convolutional Neural Networks (CNNs) for the trainin
 g phase. CNNs are chosen for their effectiveness in image recognition task
 s. The training involves adjusting the model to identify and learn from th
 e patterns and features in the training dataset. This includes resizing im
 ages for consistency\, specifying model architecture with layers designed 
 for feature extraction and classification\, and selecting optimization and
  loss functions appropriate for a multi-label classification task.\n\nThis
  project showcases the potential of applying advanced machine learning tec
 hniques to cultural heritage preservation\, offering a novel tool for cata
 loging and studying historical artifacts. It illustrates how technology ca
 n aid in the detailed analysis of cultural artifacts\, providing deeper in
 sights and facilitating easier access to information about our historical 
 heritage.
LOCATION:West 2\, West Hub
END:VEVENT
END:VCALENDAR