With the availability of millions or even billions of social media to people, a lot of new research opportunities and challenges arise for massive data analytics, such as knowledge mining from social media, deep neural network modeling for pattern analysis, transfer learning for heterogeneous media analysis, etc.
This special issue will target the most recent advances in data representation and learning algorithms which are important to the research and applications of pattern analysis. It is not difficult to enumerate a large number of successful examples in this research area, e.g., semi-supervised manifold learning has been successfully applied to large scale multimedia retrieval; multiview learning and ensemble algorithms provide attractive solutions for heterogeneous media mining; metric learning, kernel learning and causality reasoning investigate the relationship (spatial or temporal) among different patterns; and deep neural networks produces promising results in many applications.
The editors expect to collect a set of recent advances in the related topics, to provide a platform for researchers to exchange their innovative ideas on data representation and learning solutions for pattern analysis, and to bring in interesting utilizations of learning algorithms for particular pattern analysis applications.
To summarize, this special issue welcomes a broad range of submissions developing and using data representation and learning techniques for pattern analysis. We are especially interested in 1) theoretical advances as well as algorithm developments in data representation and learning for specific pattern analysis problems, 2) reports of practical applications and system innovations in pattern analysis, and 3) novel data sets as test-beds for new developments, preferably with implemented standard benchmarks. The following list contains topics of interest (but not limited to):
Advances in neural networks and learning systems
Novel deep/broad learning architectures for pattern analysis
Training techniques for deep learning
Neural network modeling and design for pattern analysis
Optimization for deep/broad representation learning
Advances in supervised, semi-supervised and supervised learning with deep/broad architectures
Novel sparse representation and coding for pattern analysis
Deep reinforcement learning algorithms
Deep transfer learning algorithms
Applications of data representation and learning
Manuscript submission: December 01, 2017
R1 Version: March 01, 2018
Acceptance notification: July 01, 2018
Final manuscripts due: August 01, 2018
Anticipated publication: TBA 2018
Papers submitted to this special issue for possible publication must be original and must not be under consideration for publication in any other journal or conference.
If the submission is an extended version of a previously published workshop or conference paper, this should also be explicitly mentioned in the cover letter, the published paper must be cited in the submitted journal paper, and the submitted journal paper must technically extend the conference version, by 30% according to Neurocomputing rules; i.e., the technical contribution in the journal version must be extended beyond what was presented in the conference version.
Authors must follow the formatting and submission instructions of Neurocomputing at https://www.elsevier.com/journals/neurocomputing/ and follow the \”Submit Your Paper\” link on that page. Please make sure you select the SI title when you submit on-line, and mention in your cover letter that you are submitting to this special issue.
Professor C. L. Philip Chen
Ph.D., FIEEE, FAAAS
Dean and Chair Professor
Faculty of Science and Technology, The University of Macau
Professor Xinge You
Professor, Vice Dean
School of Electronics and Information Communications, Huazhong University of Science and Technology
Director, National Anti-Counterfeit Engineering Research Center
Professor Weifeng Liu
China University of Petroleum (East China)
Professor Xinbo Gao
FIET, FCIE, SMIEEE
Xidian University, China,
Dr. Tongliang Liu
The University of Sydney
Email: Tongliang.Liu@ sydney.edu.au
Professor Fionn Murtagh
Department of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK.