Submission



(Available now!)

 

Submission Guidelines

Prospective authors are invited to submit full-length papers by the submission deadline. The submission of a paper implies that the paper is original and has not been submitted under review or copyright protected by the author if accepted.

All papers should be submitted electronically via Online Paper Submission System. The format of the initial submissions must be PDF.

Paper Format

Papers must be single-spaced in one column format within an area of 122 mm x 193 mm with 10-point Times-Roman font. The number of nominal pages is 12 and each additional page is subject to a surcharge of US$100.  All papers must be written in English using the Springer LNCS (Lecture Notes in Computer Science) style, including all tables, figures, and references. Download the PDF of the Authors Guidelines.

It is required that the authors use the style file of Springer Lecture Notes in Computer Science (template files for MS Word or LaTeX2e) when preparing the manuscripts to ensure the uniformity of papers.

Copyright

After uploading the final version of your accepted paper, please continue to complete the online electronic Copyright Form.


Special Session on
Spiking Neural Networks

In the era of big data, the research community finds itself with the challenge of processing complex information that belongs to a high-dimensional deep space. Novel artificial intelligence techniques have been developed that can learn complex big data and produce accurate results by means of deep learning in the neural network system. The techniques used to achieve such results are based on Spiking Neural Networks (SNN) methodologies, as they process the information available drawing inspiration from the mechanisms involved in the formation of memory and synaptic plasticity in the human brain. For this reason, they have been named the third generation of neural network processing.

There is presently considerable interest in this topic of research. SNNs have already been applied to data modelling, predictive systems, data mining, pattern recognition, in the field of bioinformatics, computational biology, biomedical engineering, cognitive computation and in any field that involves complex temporal or spatio-temporal data. This is due to their ability to model noisy data, evolve in size and work either off-line or on-line with high effectiveness. SNN technology is quickly establishing itself as an effective alternative to traditional machine learning technologies, and the interest in this area of research is growing rapidly. Bio- and Neuro- Informatics research is predict to strongly benefit from the advancement in this field.

Thus, our special session on Spiking Neural Networks For Bio- And Neuro- Informatics invites researchers to present state-of-the-art SNN techniques approaches, recent advances and their application for bio- and neuro- informatics data analysis. This special session aims to bring together research works of contemporary areas of SNN, including theoretical, computational, applicationoriented, experimental studies, and emerging technologies such as neuromorphic hardware.

The topics relevant to this special session include, but are not limited to, the following

Organizer

Nikola Kasabov, Knowledge Engineering & Discovery Research Institute (KEDRI), Auckland University of Technology (AUT), New Zealand
Elisa Capecci, Knowledge Engineering & Discovery Research Institute (KEDRI), Auckland University of Technology (AUT), New Zealand
Josafath Israel Espinosa Ramos, Knowledge Engineering & Discovery Research Institute (KEDRI), Auckland University of Technology (AUT), New Zealand
Maryam Doborjeh, Knowledge Engineering & Discovery Research Institute (KEDRI), Auckland University of Technology (AUT), New Zealand


Special Session on
Theory and Applications of Reservoir Computing

Reservoir Computing (RC) is a computational paradigm based on a special class of recurrent neural networks, suited for temporal information processing. During the last decade, considerable advances have been made in theoretical, algorithmic, and application studies on RC including the Echo State Networks and Liquid State Machines, due to its advantage in low training cost and simple architecture. Moreover, rapid progress has been made on physical and hardware implementations of RC systems in the last five years, as there are several types of potential substrates to build a dynamic reservoir compared to other kinds of recurrent neural networks.

For accelerating the development of RC, the organizers solicit papers to present state-of-the-art technologies relevant to theory, algorithm, physical implementation and practical industry applications of RC and related systems to promote stimulating open discussions in terms of neural information processing.

The topics relevant to this special session include, but are not limited to, the following

  • Theoretical and computational analysis of RC
  • Control and adaptation of RC
  • Unification of RC and other machine learning techniques
  • Physical and hardware implementations of RC
  • Applications of RC
  • Nonlinear dynamical systems for RC
  • Biological relevance of RC
  • New frameworks and models related to RC
  • Any other topics related to RC

Organizer

Gouhei Tanaka, Graduate School of Engineering, The University of Tokyo, Japan
Toshiyuki Yamane, IBM Research - Tokyo, Japan


Special Session on
Data Mining in Marketing & Social Science

As quantitative analytics become mainstream methodologies in marketing and social science, the importance of data mining has been recognized by more and more researchers in these areas. Data mining has been the central interdisciplinary methodology employed in marketing and social science research. Nowadays, new challenges have been posed by the growing volume and variety of data, and the demand for efficiency and insightfulness has been further improved. Marketing and social scientists are eager for novel mining techniques that can tackle data derived from complex exchange and social systems. The goal of this invited session is to bring together the data mining community as well as researchers from marketing and social science to set up visions on how data mining techniques can be used to achieve efficient and insightful analysis in marketing and social science research, and how marketing and social scientists can contribute in promoting methods and applications of data mining. Researchers from these areas are encouraged to submit proposals to present their work related to ensemble learning and deep learning. Submissions will be evaluated based on their innovation, relevance, scientific contribution, and presentation.

Authors are invited to submit their original and unpublished work with the topics including, but not limited to using the following techniques

  • Artificial Neural Networks
  • Support Vector Machines/Support Vector Regression
  • Evolutionary Computation
  • Fuzzy Logic
  • Expert Systems
  • Pattern Recognition
  • Knowledge Discovery
  • to address the issues below:

  • Sales/Demand Forecasting
  • Retailing and Pricing
  • Advertising
  • Customer Relationship Management
  • Brand Management
  • Social Marketing
  • Cognitive and Behavioural Sciences
  • Computational Social Science
  • Politics, Public Policy and Law

Organizer

Ying Lin, Sun Yat-sen University, China
Wei-Jie Yu, Sun Yat-sen University, China
Jing-Hui Zhong, South China University of Technology, China