Skip to main content
  • Book
  • © 2020

Reconfigurable Cellular Neural Networks and Their Applications

  • Shows readers how neural networks can be adapted for practical applications
  • Introduces new research directions based on recent findings using mixed excitatory and inhibitory neuronal populations
  • Helps readers apply neural networks to bio-inspired sensory processing tasks

Part of the book series: SpringerBriefs in Applied Sciences and Technology (BRIEFSAPPLSCIENCES)

Part of the book sub series: SpringerBriefs in Nonlinear Circuits (BRIEFSNONLINCIRC)

Buy it now

Buying options

eBook USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

This is a preview of subscription content, log in via an institution to check for access.

Table of contents (4 chapters)

  1. Front Matter

    Pages i-vi
  2. Introduction

    • Müştak E. Yalçın, Tuba Ayhan, Ramazan Yeniçeri
    Pages 1-3
  3. Artificial Neural Network Models

    • Müştak E. Yalçın, Tuba Ayhan, Ramazan Yeniçeri
    Pages 5-22
  4. Artificial Olfaction System

    • Müştak E. Yalçın, Tuba Ayhan, Ramazan Yeniçeri
    Pages 23-50
  5. Implementations of CNNs

    • Müştak E. Yalçın, Tuba Ayhan, Ramazan Yeniçeri
    Pages 51-71
  6. Back Matter

    Pages 73-74

About this book

This book explores how neural networks can be designed to analyze sensory data in a way that mimics natural systems. It introduces readers to the cellular neural network (CNN) and formulates it to match the behavior of the Wilson–Cowan model. In turn, two properties that are vital in nature are added to the CNN to help it more accurately deliver mimetic behavior: randomness of connection, and the presence of different dynamics (excitatory and inhibitory) within the same network. It uses an ID matrix to determine the location of excitatory and inhibitory neurons, and to reconfigure the network to optimize its topology.

The book demonstrates that reconfiguring a single-layer CNN is an easier and more flexible solution than the procedure required in a multilayer CNN, in which excitatory and inhibitory neurons are separate, and that the key CNN criteria of a spatially invariant template and local coupling are fulfilled. In closing, the application of the authors’ neuron population model as a feature extractor is exemplified using odor and electroencephalogram classification.


Authors and Affiliations

  • Department of Electronics and Telecommunications Engineering, Istanbul Technical University, Istanbul, Turkey

    Müştak E. Yalçın, Tuba Ayhan

  • Aeronautical Engineering, Istanbul Technical University, Istanbul, Turkey

    Ramazan Yeniçeri

About the authors

Tuba Ayhan was born in Ankara, Turkey, in 1987. She received the B.Sc. and M.Sc. degrees in electronics engineering from Istanbul Technical University, Istanbul, Turkey, in 2008 and 2010, respectively. In 2015, she received the Ph.D. degree in Applied Sciences from the Katholieke Universiteit Leuven, Belgium on electronic localization systems. She studied machine olfaction and cellular neural networks and she was a visiting scholar at The Institute for Nonlinear Science, University of California San Diego (UCSD) during her Master. Since 2015, she has been a research assistant at Istanbul Technical University, Istanbul, Turkey,

Mustak E. Yalcin was born in Unye, Turkey, in 1971. In 1993, he obtained the degree in Electronics and Telecommunications Engineering from Istanbul Technical University (I.T.U.), Electrical and Electronic Engineering Faculty. In 1997, he received the Master degree in Electronics and Communications Engineering from I.T.U. Institute of Science andTechnology. In 2004, he recieved the Ph.D. degree in Applied Sciences from the Katholieke Universiteit Leuven, Belgium. Between June 2004-December 2004, he was a postdoctoral fellow at Katholieke Universiteit Leuven, Department of Electrical Engineering (ESAT)/SCD-SISTA. He was also a Visiting Research Fellow at The Institute for Nonlinear Science, University of California San Diego (UCSD) in 2009. He is currently a full Professor with Istanbul Technical University, Turkey. His research interests are mainly in the areas of the theory and application of nonlinear circuit and systems. He is co-author of the book "Cellular Neural Networks, Multi-Scroll Chaos and Synchronization" (World Scientific). Mustak E. Yalcin has been elected Chair of IEEE CAS Cellular Nanoscale(Neural) Networks and Array Computing Technical Committee form 2015. He was appointed as Associate Editor for the International Journal of Bifurcation and Chaos in Applied Sciences and Engineering from 2015.

RamazanYeniceri was born in Denizli, Turkey in 1985. He received his B.Sc., M.Sc. and Ph.D. degrees in Electronics and Communication Engineering Department from Istanbul Technical University (ITU). He has received ITU Annual Award for Best PhD Thesis in 2015. After six years of Research and Teaching Assistant experience in ITU Department of Electronics and Communication Engineering and one year of Senior Design and Verification Engineer experience in Electra IC, he has been with ITU Aerospace Research Center (ITUARC) in a Senior Researcher position. He is now with Department of Aeronautical Engineering as Assistant Professor and Board Member of ITUARC. His current research topics are unmanned aerial vehicles, embedded systems and avionics.

Bibliographic Information

Buy it now

Buying options

eBook USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access