Benelearn CALL FOR PAPERS

Benelearn is the Annual Machine Learning Conference of Belgium and the Netherlands. It serves as a forum for researchers to exchange ideas, present recent work, and foster collaboration in the broad field of Machine Learning and its applications. The 27th edition will be held at JADS, Den Bosch, The Netherlands, on Thursday 8 and Friday 9 November, 2018,  under the auspices of the Dutch Research School for Information and Knowledge Systems (SIKS). Benelearn 2018 will be co-located with BNAIC 2018 as a two day event.

———–
SUBMISSIONS
———–

Researchers are invited to submit unpublished original research on all aspects of Machine Learning. Additionally, high-quality research results already published at international ML conferences or in ML journals are also welcome. Four types of submissions are invited:

Type A: REGULAR PAPERS
Papers presenting original work that advances Machine Learning. In addition to papers on original work, position and review papers are also welcomed. These contributions should address a well-developed body of research, an important new area, or a promising new topic, and provide a big picture view. Type A-papers can be long or short. Long papers should be 10-15 pages, short papers 6-10 pages. Contributions will be reviewed on overall quality and relevance. Type A-Papers can be accepted for either oral or poster presentation.

Type B: COMPRESSED CONTRIBUTIONS
Abstracts of already published work. Papers that have been accepted after June 1, 2017 for ML-related refereed conferences or journals can be resubmitted and will be accepted as compressed contributions. Authors are invited to submit the officially published version (without page restriction) together with a 2-page abstract. Type B-Papers will be accepted for either oral or poster presentation. Authors may submit at most one type B-paper of which they are the corresponding author.

Type C: DEMONSTRATIONS
Demonstration abstracts. Proposals for demonstration should be submitted as a 2-page abstract together with a short video illustrating the working of the system (not exceeding 15 minutes). Demonstrations will be evaluated based on their originality and innovative character, the technology deployed, the purpose of the systems in interaction with users and/or other systems, and their economic and/or societal potential. Any system requirements should also be mentioned.

Type D: THESIS ABSTRACTS
Abstracts of graduation reports. Bachelor and Master students are invited to submit a 2-page abstract of their completed ML-related thesis. Supervisors should be listed. The thesis should be accepted after June 1, 2017. Type D-papers will be judged on relevance for the conference and originality. Type D-Papers can be accepted for either oral or poster presentation.

Accepted contributions within all four categories will be included in the online conference proceedings. All contributions should be written in English, using the Springer CCIS/LNCS format (see http://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines) and submitted electronically via EasyChair (https://easychair.org/conferences/?conf=benelearn2018). Submission implies willingness of at least one author to register for BNAIC/Benelearn 2018 and present the paper. For each paper, a separate author registration is required. This year there will be an option to have papers included in postproceedings in the Springer CCIS series (http://www.springer.com/series/7899).

——————
TOPICS OF INTEREST
——————

A non-exhaustive list of topics includes:

Neural Networks
Reinforcement learning
Representation learning
Statistical Learning
Bayesian Learning
Causal Learning
Structured Output Learning
Online Learning
ML in non-stationary environments
Transfer Learning
Learning in Multi-Agent Systems
Robot Learning
Computational Learning Theory
ML and information theory
ML with expert-in-the-loop
Visual analytics and ML
Computational models of Human Learning
Evaluation frameworks
ML for scientific discovery
Social network
Deep learning
Data Mining
Predictive modeling
Ensemble Methods
Kernel Methods
Case-based Learning
Evolutionary Computation
Inductive Logic Programming
Knowledge Discovery in Databases
Pattern mining
Clustering
Feature Selection and Dimensionality Reduction
Ranking / Preference Learning / Information Retrieval
Learning for Language and Speech
Media Mining and Text Analytics
Learning and Ubiquitous Computing
Learning from Big Data
ML applications in industry
(see also Industry Track)

—————
IMPORTANT DATES
—————

September 24, 2018 (extended)   Submission due
October 22, 2018     Notification of acceptance
November 03, 2018     Final papers due
November 8-9, 2018   Conference

Please note: All deadlines are AoE time zone.