BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.4//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:ĚÇĐÄÔ­´´
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20191103T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20190310T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.361751.field_event_date.0@www.wright.edu
DTSTAMP:20260220T001025Z
CREATED:20190724T134540Z
DESCRIPTION:Committee:  Drs. Pascal Hitzler\, Advisor\, Mateen Rizki\, and 
 Yong PeiABSTRACT:In recent years\, the research in deep learning and knowl
 edge engineering has made a wide impact on the data and knowledge represen
 tations. The research in knowledge engineering has frequently focused on m
 odeling the high level human cognitive abilities\, such as reasoning\, mak
 ing inferences\, and validation.Semantic Web Technologies and Deep Learnin
 g have an interest in creating intelligent artifacts. Deep learning is a s
 et of machine learning algorithms that attempt to model data representatio
 ns through many layers of non-linear transformations. Deep learning is inc
 reasingly employed to analyze various knowledge representations mentioned 
 in Semantic Web and provides better results for Semantic Web Reasoning and
  querying.Researchers at Data Semantic Laboratory (DaSe lab) have develope
 d a method to train a deep learning model which is based on End-to-End mem
 ory network over RDF knowledge graphs which can be able to perform reasoni
 ng over new RDF graph with the help of triple normalization with high prec
 ision and recall when compared to traditional deductive algorithms. Resear
 chers have also found out that it’s 40 times faster to train than the non-
 normalized model on a dataset which they have performed experiments on. Th
 ey have created efficient model capable of transferring its reasoning abil
 ity (by applying normalization) from one domain to another without any re/
 pre-training or fine-tunning over new domain which constitutes Transfer le
 arning.In this thesis\, we are testing this Normalized embedding approach 
 on the research which is done by Bassem Makni and James Hendler “Deep Lear
 ning for Noise-tolerant RDFS reasoning” [a]. The main limitation of their 
 approach is that the training is done on a dataset that uses only one onto
 logy for the inference. In order to overcome this limitation\, we are prop
 osing transfer learning process by adding the normalization approach creat
 ed by DaSe Lab Researchers for reasoning over different ontologies/domains
 .
DTSTART;TZID=America/New_York:20190729T100000
DTEND;TZID=America/New_York:20190729T120000
LAST-MODIFIED:20190724T141736Z
LOCATION:304 Russ Engineering
SUMMARY:Masters Thesis Defense “Transfer Learning for Knowledge Graph Reaso
 ning using Normalization” By BhargavaCharan Reddy Kaithi
URL;TYPE=URI:/events/masters-thesis-defense-%E2%80%9C
 transfer-learning-knowledge-graph-reasoning-using-normalization%E2%80%9D
END:VEVENT
END:VCALENDAR