MM-INTEREST Archives

ACM SIGMM Interest List

MM-INTEREST@LISTSERV.ACM.ORG

Options: Use Forum View

Use Proportional Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
jbenoisp <[log in to unmask]>
Reply To:
Date:
Mon, 9 Mar 2020 11:13:49 +0100
Content-Type:
text/plain
Parts/Attachments:
text/plain (90 lines)
----------------We apologize if you receive this message several times--------- 

Call for papers  ICPR’2020 Workshop 

**************************Explainable Deep Learning/AI********************
https://edl-ai-icpr.labri.fr/

The recent focus of AI and Pattern Recognition communities on the supervised learning 
approaches, and particularly to Deep Learning / AI, resulted in considerable increase of 
performance of Pattern Recognition and AI systems, 
but also raised the question of the trustfulness and explainability of their predictions 
for decision-making. 
Instead of developing and using Deep NNs as black boxes and adapting known architectures 
to variety of problems, the goal of explainable Deep Learning / AI is to propose methods 
to “understand” and “explain” how the these systems produce their decisions. 
The goals of the workshop are to bring together research community which is working on 
the question of improving explainability of AI and Pattern Recognition algorithms and systems. 
The topics of the workshop cover but are not limited to:

•	“Sensing” or “salient features” of Neural Networks and AI systems - explanation of 
which features for a given configuration yield predictions both in spatial (images) and 
temporal (time-series, video) data;
•	Attention mechanisms in Deep Neural Networks and their explanation;
•	For temporal data, the explanation of which features and at what time are the most 
    prominent for the prediction and what are the time intervals when the contribution 
    of each data is important; 
•	How the explanation can help on making Deep learning architectures more sparse 
    (pruning) and light-weight;
•	When using multimodal data how the prediction in data streams are correlated and 
    explain each other;
•	Automatic generation of explanations / justifications of algorithms and systems’ 
    decisions;
•	Decisional uncertainly and explicability 
•	Evaluation of the explanations generated by Deep Learning and other AI systems.

*** Pannel:  
“Toward more explainable Deep Learning and AI systems”, Chair: Dragutin Petcovic(SFSU,USA)
Moderator will ask invited speakers to briefly present  their opinions and ideas on 
the topic of the panel and then the audience will be invited to a discussion

*** Dates:

    Submission deadline : June 15th 2020
    Workshop author notification: July 15th 2020
    Camera-ready submission: July 30th 2020
    Finalized workshop program: August 15th 2020

*** Paper Submission:

The Proceedings of the EDL-AI 2020 workshop will be published in the Springer 
Lecture Notes in Computer Science (LNCS) series. Papers will be selected by a single blind
(reviewers are anonymous) review process. Submissions must be formatted in accordance 
with the Springer's Computer Science Proceedings guidelines . Two types of contribution 
will be considered:

    Full paper (12-15 pages)
    Short papers (6-8 pages)

*** Submission site: coming soon

Program Committee: 

Christophe Garcia (LIRIS, France) 
Hugues Talbot (EC, France) 
Dragutin Petkovic (SFSU,USA) 
Alexandre Benoît( LISTIC,France) 
Mark T. Keane (UCD, Ireland)
Georges Quenot(LIG, France) 
Stefanos Kolias (NTUA, Grece) 
Jenny Benois-Pineau(LABRI, France)
Hervé Le Borgne (LIST, France)
Noel O’Connor (DCU, Ireland)
Nicolas Thome(CNAM, France)


Jenny Benois-Pineau, Georges Quenot
Workshop Organizers

Jenny Benois-Pineau, 
Professeure en Informatique, 
Chargée de mission aux relations Internationales
Collège Sciences et Technologies, 
Université de Bordeaux

Jenny Benois-Pineau, PhD, HDR, 
Professor of Computer Science, 
Chair of International relations
Faculty of Sciences and Technologies
University of Bordeaux 

ATOM RSS1 RSS2