Special Session

Complex- and Hypercomplex-valued Neural Networks

IJCNN 2025 - Special Session

Aim and Scope.


Complex-valued and, more generally, hypercomplex-valued neural networks (HVNNs) constitute a rapidly growing research area that has attracted continued interest for the last decade. Besides their natural ability to treat multidimensional data, hypercomplex-valued neural networks can benefit from hypercomplex numbers’ geometric and algebraic properties. For example, complex-valued neural networks are essential for adequately treating phase and the information contained in phase, including the treatment of wave- and rotation-related phenomena such as electromagnetism, light waves, quantum waves, and oscillatory phenomena. Quaternion-valued neural networks, which naturally incorporate spacial rotations and have potential applications in three- and four-dimensional data modeling, have been effectively used to process and analyze multivariate images such as color and polarimetric SAR images. Despite significant theoretical development and successful applications, many research directions in HVNNs remain in progress. These include formally generalizing the commonly used real-valued network architectures and training algorithms to the hypercomplex-valued case. There are also many exciting applications in pattern recognition and classification, nonlinear filtering, intelligent image processing, brain-computer interfaces, time-series prediction, bioinformatics, and robotics, to list a few. This special session aims to be the proper forum for a systematic and comprehensive exchange of ideas, presenting recent research results and discussing future trends in complex- and hypercomplex-valued neural networks. We hope the proposed session will attract potential speakers and researchers interested in joining the community. We also expect this session to benefit and inspire computational intelligence researchers and other specialties that need sophisticated neural network tools.

List of Topics.


This special session welcomes papers that are or might be related to all aspects of complex- and hypercomplex-valued neural networks. Contributions to theoretical advances or applications are all appreciated. We also welcome interdisciplinary contributions from other areas on the proposed scope's borders. Topics include, but are not limited to:

Past Special Sessions.


Special sessions on complex- and hypercomplex-valued neural networks have become a traditional event of the IJCNN conference. Thirteen special sessions have been organized since 2006, namely:

  1. WCCI-IJCNN 2006, Vancouver - Canada;
  2. WCCI-IJCNN 2008, Hong Kong - China;
  3. IJCNN 2009, Atlanta - USA;
  4. WCCI-IJCNN 2010, Barcelona - Spain;
  5. IJCNN-2011, San Jose - USA;
  6. WCCI-IJCNN 2012, Brisbane - Australia;
  7. IJCNN-2013, Dallas - USA;
  8. WCCI-IJCNN 2014, Beijing - China;
  9. WCCI-IJCNN 2016, Vancouver - Canada;
  10. WCCI-IJCNN 2018, Rio De Janeiro - Brazil;
  11. WCCI-IJCNN 2020, Glasgow - UK;
  12. WCCI-IJCNN 2022, Padua - Italy;
  13. WCCI-IJCNN 2024, Yokohama - Japan
These special sessions attracted numerous submissions and had large audiences. They featured many engaging presentations and very productive discussions. Because of the recent advances in complex- and hypercomplex-valued neural networks, we expect this special session to be as exciting and fruitful as the past special sessions.

Organizers.


Marcos Eduardo Valle

Universidade Estadual de Campinas (Unicamp), Brazil
Email: valle@ime.unicamp.br
URL: http://www.ime.unicamp.br/~valle

Eckhard Hitzer

International Christian University, Japan
Email: hitzer@icu.ac.jp
URL: https://researchers.icu.ac.jp/icuhp/KgApp?resId=S002377&Language=2

João Paulo Papa

Universidade Estadual Paulista (UNESP), Brazil
Email: joao.papa@unesp.br
URL: https://papajpblog.wordpress.com/about/

Akira Hirose

University of Tokyo, Japan
Email: ahirose at ee.t.u-tokyo.ac.jp
URL: www.eis.t.u-tokyo.ac.jp/~ahirose

Important Dates.


We are looking forward to seeing you in Rome!

Powered by w3.css