BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:5740-2022@rg-bremen-oldenburg.gi.de
CLASS: PUBLIC
SUMMARY:Accessing the Hidden Space with Explainable Artificial Intelligence
DESCRIPTION:Abstract: The emerging field of explainable Artificial Intellig
 ence (XAI) aims to bring transparency to today’s powerful but opaque deep l
 earning models. However, the vast majority of current approaches to XAI onl
 y provide partial insights and leave interpreting the model’s reasoning to 
 the user. This talk will provide an overview on how established techniques 
 from XAI can be used to successfully understand, debug and improve machine 
 learning models and pipelines. The session will provide an outlook on how r
 ecent developments towards concept-based XAI (with a focus on the recent Co
 ncept Relevance Propagation (CRP) approach) will lead to more human interpr
 etable explanations and thus enable novel analyses to gain insights into th
 e reasoning of AI.\n\n--- Short Bio:\n\nSebastian Lapuschkin received the P
 h.D. degree with distinction from the Berlin Institute of Technology in 201
 8 for his pioneering contributions to the field of Explainable Artificial I
 ntelligence (XAI) and interpretable machine learning. From 2007 to 2013 he 
 studied computer science (B. Sc. and M. Sc.) at the Berlin Institute of Tec
 hnology, with a focus on software engineering and machine learning. Current
 ly, he is the Head of the Explainable Artificial Intelligence at Fraunhofer
  Heinrich Hertz Institute (HHI) in Berlin. He is the recipient of multiple 
 awards, including the Hugo-Geiger-Prize for outstanding doctoral achievemen
 t and the 2020 Pattern Recognition Best Paper Award. His work is focused on
  pushing the boundaries of XAI, e.g, for achieving human-understandable exp
 lanations, or towards the utilization of interpretable feedback for the imp
 rovement of machine learning systems and data. Further research interests i
 nclude efficient machine learning and data analysis, data and algorithm vis
 ualization.
LOCATION:Universität Bremen
DTSTAMP:20230620T115010Z
DTSTART:20230627T141500Z
DTEND:20230627T160000Z
END:VEVENT
END:VCALENDAR