[UAI] ICNC-FSKD 2017 Submissions due 15 March: Submitting to IEEE Xplore/EI Compendex/ISI 2017/3/12 16:29:24 a1igm

[Prof Zhang]

Dear Colleague,

We cordially invite you to submit a paper to the upcoming 2017 13th 
International Conference on Natural Computation, Fuzzy Systems and Knowledge 
Discovery (ICNC-FSKD 2017), to be held from 29-31 July 2017 in Guilin, China. 

Guilin has long been praised as the most picturesque place in China, as an old 
Chinese saying goes: "Guilin mountain/water scenery is the best under heaven." 
Embraced by lofty hills with the winding Li River flowing through, Guilin 
boasts magnificent natural beauty and many precious cultural relics, most 
famously the Elephant Trunk Hill, Reed Flute Cave, Seven-Star Park, Folded 
Brocade Hill, plus limpid lakes, grotesque rocks, unique rice terraces and 
minority villages.

As with the past ICNC-FSKD conferences, all papers in conference proceedings 
will be submitted to EI Compendex, Scopus, and ISTP (ISI Proceedings), as well 
as IEEE Xplore (all previous ICNC-FSKD conferences from 2005 to 2016 have been 
indexed in Ei Compendex). Extended versions of selected best papers will appear 
in SCIE-indexed international journals, such as Soft Computing (Impact Factor: 
1.63), Neurocomputing (Impact Factor: 2.39), Concurrency and Computation: 
Practice and Experience (Impact Factor: 0.942). ICNC-FSKD 2017 is technically 
co-sponsored by the IEEE Circuits and Systems Society (pending).

ICNC-FSKD is a premier international forum for scientists and researchers to 
present the state of the art of data mining and intelligent methods inspired 
from nature, particularly biological, linguistic, and physical systems, with 
applications to computers, circuits, systems, control, robotics, 
communications, and more. This is an exciting and emerging interdisciplinary 
area in which a wide range of theory and methodologies are being investigated 
and developed to tackle complex and challenging problems. The registration fee 
of US-D460 includes proceedings, lunches, dinners, banquet, coffee breaks, and 
all technical sessions.

To promote international participation of researchers from outside the 
country/region where the conference is held (i.e., China’s mainland), 
researchers outside of China’s mainland are encouraged to propose invited 
sessions. An honorarium of US-D400 will be enjoyed by the organizer(s) for each 
completed (with at least 6 registered papers) invited session. The first author 
of each paper in an invited session must not be affiliated with an organization 
in China’s mainland. "(Invited Paper)" may be added below the title of each 
paper in the invited sessions. Invited session organizers will solicit 
submissions, conduct reviews and recommend accept/reject decisions on the 
submitted papers. Invited session organizers will be able to set their own 
submission and review schedules, as long as a set of recommended papers is 
determined by 3 June 2017. Each invited session proposal should include: (1) 
the name, bio, and contact information of each organizer of the invited 
session; (2) the title and a short synopsis of the invited session. Please send 
your proposal to icnc-fskd2...@guet.edu.cn

For more information, visit the conference web page:

http://cloud.guet.edu.cn/icnc_fskd/

If you have any questions after visiting the conference web page, please email 
the secretariat at 

icnc-fskd2...@guet.edu.cn

Join us at this major event in beautiful Guilin !!!

Organizing Committee
icnc-fskd2...@guet.edu.cn

P.S.: Kindly forward to your colleagues and students in your school/department.

If you wish to unsubscribe, in which case we apologize, please reply with " 
unsubscribe uai@engr.orst.edu " in your email subject. Thanks.


2017/3/12 16:29:24 ufrxe___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] Special Issue on Deep Reinforcement Learning in the journal Neural Networks

[Professor Ron Sun]

Call for Papers:  Special Issue on Deep Reinforcement Learning in Neural 
Networks
https://www.journals.elsevier.com/neural-networks/call-for-papers/special-issue-on-deep-reinforcement-learning-in-neural-netwo
 



Deep learning (DL) has become highly popular in recent years, among 
theoretically minded and application-focused researchers alike. Moreover, the 
idea of deep learning has been combined with reinforcement learning (RL), 
leading to deep reinforcement learning, which has achieved notable successes in 
tackling difficult problems, including the achievement of AlphaGo.

However, there are many open questions and issues that need to be addressed 
with regard to deep RL.  Open questions with regard to deep RL include:
·  How do we extend RL algorithms or systems to make them suitable for deep 
learning? How do we make RL (typically centered on values of states or 
state-action pairings) appropriately deep?
·  How do we do so without jeopardizing useful characteristics of RL?
·  What modification and enhancements to learning algorithms are necessary 
to accomplish deep RL in an effective and/or efficient manner?
·  How can we make knowledge within deep RL systems explicit (generating 
explicit, symbolic, usable knowledge) and enable metacognitive reflection and 
regulation to some extent?  
·  How can deep learning help facilitate planning or model-based 
reinforcement learning?
·  How can hierarchical or modular approaches be applied to deep RL?
·  What theoretical/mathematical properties can be obtained with regard to 
deep RL (e.g., convergence, stability, robustness, and optimality)?
·  How do we apply deep RL in real-world scenarios?

The aim of this special issue is to showcase state-of-the-art work in the field 
of deep RL, addressing some of the above questions and beyond. Although there 
have no doubt been advances in addressing these questions, there is clearly 
room for further development. This special issue will provide a platform for 
deep learning and reinforcement learning researchers to share their work, for 
the sake of more rapid advances on a solid footing, fully realizing the 
potential of infusing reinforcement learning and deep learning. It also intends 
to showcase more effective applications in a variety of fields (robotics, 
control engineering, data analysis, and so on).

We invite original research contributions on deep reinforcement learning 
(broadly defined). Possible topics for this special issue include, among others:
·  New and better deep RL algorithms
·  New and better neural network architectures for deep RL
·  Better combinations of existing algorithms and techniques for deep RL
·  Theories regarding deep RL
·  Mathematical analysis of deep RL  (regarding convergence, optimality, 
stability, robustness, and so on)
·  Transfer learning and prior knowledge within deep RL
·  Coping with uncertainty in deep RL
·  Combining policy learning, value learning, and model-based search
·  Symbolic structures from or within deep RL
·  Planning and deep RL
·  Hierarchical or modular RL
·  Multi-agent RL
·  Applications of deep RL algorithms, architectures, and systems to 
robotics, control, data analysis, prediction and forecast, modeling and 
simulation, and so on
·  Applications of deep RL to cognitive-psychological or social modeling 
and analysis
Survey papers are welcome also.

Submission Procedure:
Prospective authors should follow the standard author instructions for Neural 
Networks, and submit manuscripts online at http://ees.elsevier.com/neunet/ 
. During submission, authors should indicate 
that their papers are for the special issue.

Important Dates
•   July 1, 2017 – Deadline for submission
•   December 1, 2017 – Notification of review decisions to authors
•   February 1, 2018 – Deadline for submission of revised versions
•   April 1, 2018 – Final acceptance decision

Guest Editors:

Ron Sun, Ph.D.
Professor, Cognitive Science Department
Rensselaer Polytechnic Institute
110 Eighth Street, Carnegie 302A
Troy, NY 12180, USA
http://sites.google.com/site/drronsun 

David Silver, Ph.D
Google DeepMind, London
University College London
http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Home.html 


Gerald Tesauro, Ph.D
Principal Research Staff Member
Thomas J. Watson Research Center,
Yorktown Heights, NY, USA
http://researcher.watson.ibm.com/researcher/view_person_pubs.php?person=us-gtesauro&t=1
 


Guang-Bin Huang, PhD 
Professor, School of Electrical and Electronic Engineering
Nanyang Technological University
Nanyang Avenue, 
Sing

[UAI] 1st CFP: ACM RecSys'17 Workshop on Intelligent Recommender Systems by Knowledge Transfer and Learning (RecSysKTL)

[Yong Zheng]

*** Apologies for multiple postings ***







2017 International Workshop on Intelligent Recommender Systems by Knowledge
Transfer and Learning (RecSysKTL)

held in conjunction with ACM Conference on Recommender Systems, Como,
Italy, Aug 27, 2017





*Important Dates:*

June 22th, Paper Submission
July 7th, Acceptance Notification
July 17th, Camera-Ready Submission
August 27th, Workshop Date





Recommender systems, as one of well-known Web intelligence applications,
aim to alleviate the information overload problem and produce item
suggestions tailored to user preferences. Typically, user preferences or
tastes are collected through users’ implicit or explicit feedback in
various formats, such as user ratings, online behaviors, text reviews, etc.
Also, user feedback on different items can be collected from several
systems or domains. The diversity of feedback formats and domains provides
multiple views to users’ preferences, and thus, can be helpful in
recommending more related items to users. Cross-domain recommender systems
and transfer learning approaches propose to take advantage of such
diversity of viewpoints to provide better-quality recommendations and
resolve issues such as the cold-start problem.

The emerging research on cross-domain, context-aware and multi-criteria
recommender systems, has proved to be successful. Given the recent
availability of cross-domain datasets and novelty of the topic, we organize
the 1st workshop on intelligent recommender systems by knowledge transfer
and learning (RecSysKTL ) held in
conjunction with the 11th ACM Conference on Recommender Systems
. This workshop intends to create a
medium to generate more practical and efficient predictive models or
recommendation approaches by leveraging user feedbacks or preferences from
multiple domains. This workshop will be beneficial for both researchers in
academia and data scientists in industry to explore and discuss different
definition of domains, interesting applications, novel predictive models or
recommendation approaches to serve the knowledge transfer and learning from
one domain to another.

The definition of “domain” may vary in different applications, e.g., it
could be (but not limited to):

·*From one application to another:* We may utilize user behaviors
on social networks to predict their preferences on movies (e.g., Netflix,
Youtube) or music (e.g., Pandora, Spotify).

·*From one category to another:* We may predict a user’s taste on
electronics by using his or her preference history on books based on the
data collected from Amazon.com.

·*From one context to another:* We may collect a user’s preferences
on the items over different time segment (e.g., weekend or weekday) and
predict her preferences on movie watching within another context (e.g.,
companion and location).

·*From one task to another:* It may be useful for us to predict how
a user will select hotels for his or her vocations by learning from how he
or she books the tickets for transportations.

·*From one structure to another:* It could be also possible for us
to infer social connections by learning from the structure of heterogeneous
information neworks.

Generally, we focus on the topic of “cross-domain”, where the notion of
“domain” may vary from applications to applications. For example, the
concept of context-aware and multi-criteria recommender systems can also be
considered as an application of “cross-domain” techniques. Particularly, we
are interested in how to apply knowledge transfer and learning approaches
to build intelligent recommender systems.

The topics of interest include (but are not limited to):

·*Applications of Knowledge Transfer for Recommender Systems*

·Cross-domain recommendation

·Context-aware recommendation, time-aware recommendation

·Multi-criteria recommender systems

·Novel applications

·*Methods for Knowledge Transfer in Recommender Systems*

·Knowledge transfer for content-based filtering

·Knowledge transfer in user- and item-based collaborative filtering

·Transfer learning of model-based approaches to collaborative
filtering

·Deep Learning methods for knowledge transfer

·*Challenges in Knowledge Transfer for Recommendation*

·Addressing user feedback heterogeneity from multiple domains (e.g.
implicit vs. explicit, binary vs. ratings, etc.)

·Multi-domain and multi-task knowledge representation and learning

·Detecting and avoiding negative (non-useful) knowledge transfer

·Ranking and 

[UAI] 1st CFP: WPRSM'17: The International Workshop on Web Personalization, Recommender Systems and Social Media

[Yong Zheng]

*** Apologies for multiple postings ***





=



WPRSM'17: The International Workshop on Web Personalization, Recommender
Systems and Social Media

Conjunction with the 2017 IEEE/WIC/ACM International Conferences on Web
Intelligence, Leipzig, Germany

August 23, 2017.



Workshop website: http://www.webpres-workshop.com/

=



Important Dates:



Electronic submission of full papers: 1 May 2017

Notification of paper acceptance: 28 May 2017

Workshop:  23 August 2017

Conference: 24 - 26 August 2017



With the explosive growth of resources available through the Internet,
information overload has become a serious issue.

Especially the emergence of social media has created highly interactive
platforms for users to create, share, exchange

information and build social networks. Web users are commonly overwhelmed
by huge volume of information and are faced

with the challenge of finding the most relevant information. Recommender
systems represent tools for efficient selection

of the most relevant information resources, and the interest in such
systems has increased dramatically over the last

few years. However, web personalization has not yet been well-exploited;
difficulties arise while selecting resources

through recommender systems from technology perspective and social
perspective; also solutions are needed for effective

interaction & collaboration between users and maintain trustworthiness and
reliability of information on social media.

The aim of this workshop is to promote high quality research in technical
and human aspects related to Web personalization,

social media and resource selection through recommender systems. The
workshop will provide a forum for academic and

industrial researchers to exchange ideas about past, present and future
trends in Web personalization, social media

and resource selection, and for discussing new and innovative approaches.



We solicit contributions that advance the technology in related areas.



The topics include, but are not limited to:



•User behaviour modelling and personalization techniques

•Collaborative and content based filtering

•Clustering and classification in recommender systems

•Hybrid recommender systems

•Security and trust in recommender systems

•Trust and reputation management

•Ontology learning and semantic web technologies

•Content management and modelling

•Product modelling, user opinion mining and data extraction

•Adaptive user interfaces

•Recommender applications for social media sites

•Explanation and justification in recommender systems

•Distributed and peer-to-peer recommender systems

•Modelling decision making in e-commerce systems

•Measuring personalization effectiveness

•Evaluation methods for recommender systems

•Ownership of social media content

•Security and Privacy in social media

•Trustworthiness and reliability on social media



Paper Submission:



Paper submissions should be limited to a maximum of 4 pages (IEEE-CS
format, extra payment is only available for one more

extra page). The papers must be in English and should be formatted
according to the IEEE column format. The style files for

paper submission can be obtained from the WI2017 site or
http://webintelligence2017.com/participants/submissions/#submission.



All submitted papers will be reviewed by at least 2 program committee
members on the basis of technical quality, relevance,

significance, and clarity. The accepted papers will be included in the
Workshop Proceedings published by the IEEE Computer

Society Press.



The workshop only accepts online submissions.

Workshops online submission page can be accessed through the WI2017
Submission Site:

https://wi-lab.com/cyberchair/2017/wi17/index.php





Organizers:

Yue Xu, Queensland University of Technology, Australia

Gabriella Pasi, University of Milano Bicocca, Milano, Italy

Yuefeng Li, Queensland University of Technology, Australia

Yong Zheng, Illinois Institute of Technology, Chicago, USA
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] AlCoB 2017: call for posters

[GRLMC]

AlCoB 2017: call for posters*To be removed from our mailing list, please 
respond to this message with UNSUBSCRIBE in the subject line*


**


The 4th International Conference on Algorithms for Computational Biology (AlCoB 
2017) invites researchers to submit poster presentations. AlCoB 2017 will be 
held in Aveiro (Portugal) on June 5-7, 2017. See 


http://grammars.grlmc.com/AlCoB2017/


Poster presentations are intended to enhance informal interactions with 
conference participants, at the same time allowing for in-depth discussion.


TOPICS


Presentations displaying novel work in progress on algorithms in computational 
biology are encouraged on the following topics:


- assembling sequence reads into a complete genome,

- identifying gene structures in the genome,

- recognizing regulatory motifs,

- aligning nucleotides and comparing genomes,

- reconstructing regulatory networks of genes, and

- inferring the evolutionary phylogeny of species.


Posters do not need to show final research results. Work that might lead to new 
interesting developments is welcome.


KEY DATES


Poster submission deadline: April 28, 2017

Notification of poster acceptance or rejection: May 5, 2017


SUBMISSION


Please submit a .pdf abstract through:


https://easychair.org/conferences/?conf=alcob2017


It should contain the title, author(s) and affiliation, and should not exceed 
500 words.


PRESENTATION


Posters will be allocated 10 minutes each in the programme for oral 
presentation. Moreover, they will remain hanging out during the whole 
conference for discussion.


PUBLICATION


Posters will not appear in the LNCS/LNBI proceedings volume of AlCoB 2017. 
However, they will be eligible for submission to the post-conference journal 
special issue in the Journal of Computational Biology (2015 JCR impact factor: 
1.537).


REGISTRATION


At least one author of each accepted poster must register to the conference by 
May 22, 2017. The registration fare is reduced: 260 Euro. It gives the same 
rights all other conference participants have (attendance, copy of the 
proceedings volume, lunches...). Contributors of regular papers who in addition 
get a poster accepted must register for the latter independently.
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai

[UAI] CFP: Extended deadline 23 March. The 3rd IEEE International Conference on Cybernetics (CYBCONF-2017) and Journal Special Issues, 21-23 June 2017

[Haozhe Wang]

[Please accept our apologies if you receive multiple copies of this CFP]

** IEEE CYBCONF-2017 CFP
*

*The 3rd IEEE International Conference on Cybernetics*

*(CYBCONF-2017)*

http://cse.stfx.ca/~CybConf2017

*Exeter, England, UK, 21-23 June 2017*

*Sponsored by*
IEEE;

IEEE Systems, Man, and Cybernetics Society (SMC).



*and supported by*

IEEE SMC Technical Committees on Cybermatics for Cyber-enabled Worlds;

IEEE SMC Technical Committees on Awareness Computing;

IEEE SMC Technical Committees on Intelligent Industrial Systems;

IEEE SMC Technical Committees on Distributed Intelligent Systems.



*** The paper submission deadline is extended to 23 March 2017 ***



INTRODUCTION
=

The biennial International Conference on Cybernetics (CYBCONF) provides a
premier international forum for researchers and practitioners to report the
latest innovations, summarize the state-of-the-art, and exchange ideas and
advances in all aspects of Cybernetics. Apart of the main track it includes
special sessions and plenary talks by invited eminent speakers.

CYBCONF-2017 is organized by University of Exeter, sponsored by IEEE
Systems, Man, and Cybernetics Society (SMC), and supported by IEEE SMC
Technical Committees on Cybermatics for Cyber-enabled Worlds, Awareness
Computing, Intelligent Industrial Systems; and Distributed Intelligent
Systems. CYBCONF-2017 will be hosted in Exeter, the capital city of Devon
and provides the county with a central base for education, medicine,
religion, commerce and culture. The city is also home to the magnificent
Exeter Cathedral, which dates back to Norman times. Exeter is also ideally
placed to base a trip to branch out visiting places such as the famous
Dartmoor National Park and the unspoilt beaches of the North and South
Devon coastlines.

Prospective authors are invited to submit their papers to CYBCONF-2017.
Accepted papers will appear in the conference proceedings, available on
IEEE Xplore and submitted to be indexed in CPCi (ISI conferences and part
of Web of Science) and Engineering Index (EI). The authors of selected best
papers will be invited post conference to extend their contributions for
special issues of prestigious journals, such as IEEE Transactions on
Cybernetics
, IEEE SMC
Magazine, Evolving Systems, and Peer-to-Peer Networking and Applications
(PPNA).



IMPORTANT DATES


·   Paper Submission Deadline:   23 March 2017

·   Authors Notification:  22 April 2017

·   Camera-Ready Paper Due: 15 May 2017

·   Early Registration Due:  15 May 2017

·   Conference Date:21-23 June 2017



JOURNAL SPECIAL ISSUES

==

Distinguished papers selected from the conferences and associated
workshops, after further extensions, will be recommended for submission and
publication in the following prestigious journals or their Special Issues:

- IEEE Transactions on Cybernetics


- IEEE Systems, Man, and Cybernetics Magazine

- Evolving Systems (Springer)

- Peer-to-Peer Networking and Applications (Springer)



PAPER SUBMISSION GUIDELINE
==

All papers need to be submitted electronically through the conference
submission website ( http://cse.stfx.ca/~CybConf2017/sub/ ) with PDF
format. The materials presented in the papers should not be published or
under submission elsewhere. Each paper is limited to 6 pages (or 8 pages
with over length charge) including figures and references using IEEE
Computer Society Proceedings Manuscripts style (two columns, single-spaced,
10 fonts). You can confirm the IEEE Computer Society Proceedings Author
Guidelines at the following web page:

http://www.computer.org/web/cs-cps/

Manuscript Templates for Conference Proceedings can be found at

https://www.ieee.org/conferences_events/conferences/publishing/templates.html

Accepted papers will appear in the conference proceedings, available on
IEEE Xplore and submitted to be indexed/abstracted in CPCi (ISI conferences
and part of Web of Science) and Engineering Index. The authors of selected
best papers will be invited post conference to extend their contributions
for special issues of prestigious journals.
___
uai mailing list
uai@ENGR.ORST.EDU
https://secure.engr.oregonstate.edu/mailman/listinfo/uai