Special Session on
“Recent Trends on Hypercomplex-valued Neural Networks”

Aim and Scope

Hypercomplex-valued neural networks (HvNNs) constitute a growing area of research that has attracted continued interest over the past decades. Unlike traditional real-valued networks, HvNNs treat multidimensional data as a single entity. There are several new research directions on HvNNs: from the formal generalization of commonly used real-valued models to their mathematically richer hypercomplex-valued counterparts to the use of appropriate activation functions that can significantly increase neuron and network functionalities. There are also many exciting applications of HvNNs in pattern recognition and classification, non-linear filtering, intelligent image processing, natural language processing, brain-computer interfaces, time series prediction, bioinformatics, robotics, etc.

The broad class of HvNNs includes complex-valued neural networks (CvNNs) and quaternion-valued neural networks (QvNNs) as examples. Essential characteristics of CvNNs are the proper treatment of the phase and the information contained in the phase and an excellent capability to cope with wave-related phenomena such as electromagnetism, light waves, quantum waves, and oscillatory phenomena. QvNNs, which have potential applications in three-dimensional and four-dimensional data modeling, have been effectively used for multivariate image processing and analysis, such as color and polarimetric SAR images; generation of synthetic data, such as text, video, image, or sound; and for natural language processing, with an emphasis on automatic speech recognition and opinion mining.

We hope this special session will inaugurate a fertile locus at the ICETCI to share recent research results and future works on HvNNs. We also hope this session will inspire and generate benefits for the community of researchers in Computational Intelligence.

This special session welcomes theoretical and applied contributions to hypercomplex-valued neural networks and related fields, including but not limited to the following topics:

  • Dynamics of hypercomplex-valued Hopfield neural networks;
  • Image processing and analysis using HvNNs;
  • Natural language processing and analysis using HvNNs;
  • Approximation properties and efficient learning rules for HvNNs;
  • Deep hypercomplex-valued networks and their applications;
  • Applications of HvNNs for healthcare and medical diagnosis;
  • Applications of HvNNs for Industry 4.0 and cybersecurity;
  • Applications of HvNNs for remote sensing.

Paper Submission

Potential authors may submit their manuscripts for presentation consideration through ICETCI 2022 submission system electronically at, following the conference guidelines. All submissions will go through peer review process. To submit your paper to this special session, you have to choose our special session title on the submission page

Important Dates

Paper submission deadline: February 15, 2022
Paper acceptance notification date: May 15, 2022
Final paper submission and early registration deadline: May 31, 2022


Marcos Eduardo Valle, University of Campinas, Brazil, Email:

Marcos Eduardo Valle received his master’s and Ph.D. degrees in applied mathematics at the University of Campinas in 2005 and 2007, respectively. He previously worked at the University of Londrina, Brazil. He is currently an associate professor at the Department of Applied Mathematics of the University of Campinas, Brazil. His research interests include associative memories, fuzzy set theory, lattice theory, mathematical morphology, hypercomplex-valued neural networks, pattern recognition, and data recovery.

Fidelis Zanetti de Castro, Federal Institute of Education, Science and Technology of Espírito Santo at Serra, Brazil, Email:

Fidelis Zanetti de Castro received his master's degree in mathematics at the Federal University of Espírito Santo in 2013. He received his Ph.D. in applied mathematics at the University of Campinas in 2018. He is currently an associate professor at the General Coordination of Education of the Federal Institute of Education, Science, and Technology of Espírito Santo at Serra, Brazil. His research interests are aimed at associative memories, hypercomplex-valued neural networks, pattern recognition, deep neural networks, and image and natural language processing and analysis.

Rama Murthy Garimella, Mahindra University École Centrale School of Engineering, India, Email:

Rama Murthy Garimella received his B.Tech. from S.V.U. College of Engineering, Tirupati, India. He received his MS in Electrica Engineering from Louisiana State University, Baton Rouge, USA, and Ph.D. in Computer Engineering from Purdue University, West Lafayette, USA. He was a member of Technical Staff at Bellcore, USA. He was an Associate Professor at the International Institute of Information Technology, Hyderabad, India. Currently, he is a Professor in the Computer Science Department of Mahindra Ecole Centrale, Hyderabad, India. His current research interests include wireless networks, IoT, and machine learning. He has 250 publications to his credit (out of which 70 are in journals). He is a senior member of ACM and a Fellow of IETE, India. He received many awards, including Rashtriya Gaurav Award from IIFS, India