Cellular neural networks and their applications

• Main Author: Tetzlaff, Ronald
• Format: eBook
• Language: English
• Published: Singapore World Scientific Publishing Co. Pte. Ltd 2002; World Scientific Publishing Company
• Edition: 1
• Subjects: Computer Science; Congresses; Networking; Neural Networks; Nonlinear systems
• ISBN: 9789812381217; 981238121X

Table of Contents:

• Cellular neural networks and their applications -- Foreword -- Contents -- Keynote Address; The Origin of Complexity (presented, but paper not submitted) -- Plenary Session; The Role of Field Coupling in Nano-Scale Cellular Nonlinear Networks -- Session Theory I; On the Relationship Between CNNs and PDEs -- New Spatial-Temporal Patterns and the First Programmable On-Chip Bifurcation Test-Bed -- On Stability of Full Range and Polynomial Type CNNs -- A Study on Limit Cycles in Nearly Symmetric Cellular Neural Networks -- An Improved Global Stability Result for Cellular Neural Networks with Time Delay -- Session Applications I; SC-CNNs for Chaotic Signals Generation -- Moving Object Tracking on Panoramic Images -- MPEG-4 Based Modifications for an CNN Segmentation Chip -- Watermarking for the Authentication of Video on CNN-UM -- An Analogic CNN-Algorithm of Pixel Level Snakes for Tracking and Surveillance Tasks -- Session Theory II; On the Dynamics of a Class of Cellular Neural Networks -- mL-CNN: A CNN Model for Reaction-Diffusion Processes in m-Component Systems -- Emergence of Global Patterns in Connected Neural Networks -- Influence of System Non-Uniformity on Dynamic Phenomena in Arrays of Coupled Nonlinear Networks -- Boolean Design of Binary Initialized and Coupled CNN Image Processing Operators -- Session Physical Implementations I; ACE16K: A 128x128 Focal Plane Analog Processor with Digital I/O. -- On the RTD Implementation of Simplicial Cellular Nonlinear Networks -- Programmable Optical CNN Implementation Based on the Template Pixels' Angular Coding -- Application Issues Of A Programmable Optical CNN Implementation -- Configurable Multi-Layer CNN-UM Emulator on FPGA -- Session Applications II (Poster); Object-Oriented Image Analysis via Analogic CNN Algorithms - Part I: Motion Estimation -- Object-Oriented Image Analysis via Analogic CNN Algorithms - Part II: Image Synthesis and Consistency Observation -- A CNN Path Planning for a Mobile Robot in an Environment with Obstacles -- A CNN Based System to Blind Sources Separation of MEG Signals -- Delay-Driven Contrast Enhancement Using a Cellular Neural Network with State-Dependant Delay -- Plenary Session; Time as Coding Space for Information Processing in the Cerebral Cortex -- Characterizing the Spatio-Temporal Dynamics of the Epileptogenic Process with Nonlinear EEG Analyses -- Session Bionics and Biologically Relevant Models I; Analyzing Multidimensional Neural Activity via CNN-UM -- Basic Mammalian Retinal Effects on the Prototype Complex Cell CNN Universal Machine -- Prediction of Epileptic Seizures by CNN with Linear Weight Functions -- Biometric Authentication Based on Perceptual Resonance between CNN Emergent Patterns and Humans -- CNN Based Central Pattern Generators with Sensory Feedback -- Session Integrated Sensing and Processing; Mobile Sensor-Actuator Networks: Opportunities and Challenges -- Visual Feedback by Using a CNN Chip Prototype System -- Multi-Target Tracking with Stored Program Adaptive CNN Universal Machines -- CNN-based 3D Thermal Modeling of the Soil for Antipersonnel Mine Detection -- PDE Based Histogram Modification with Embedded Morphological Processing of the Level-Sets -- Plenary Session; Computational and Computer Complexity of Analogic Cellular Wave Computers -- Session Physical Implementations II; Design of Min/Max Cellular Neural Networks (MMCNNS) in CMOS Technology -- Improved ARAM for PARIS, an Original Programmable Vision Chip -- An Accelerated Digital CNN-UM (CASTLE) Architecture by Using the Pipe-Line Technique -- PDE-DPCNN: A CNN Chip for Analogue Simulations of RD Equations -- Chaotic Phenomena in Quantum Cellular Neural Networks -- Session Applications III; Fingerprint Image Enhacement Using CNN Gabor-Type Filters -- Obstacle Detection in Planar Worlds Using Cellular Neural Networks -- Potential Anomaly Separation Using Genetically Trained Multi-Level Cellular Neural Networks -- Fragile Watermarking and Unkeyed Hash Function Implementation for Image Authentication on CNN-UM -- Analogic Preprocessing and Segmentation Algorithms for Off-Line Handwriting Recognition -- Session Cellular and Sparsely Connected Dynamic Processor Systems (Poster); Nonlinear Dynamics and Propagation in Positive Feedback Comparators for A/D Converters -- Realization of Couplings in a Polynomial Type Mixed-Mode CNN -- A Cellular Fuzzy Associative Memory for Bidimensional Pattern Segmentation -- A/D and D/A Converters in a Mixed-Mode CNN -- Session Bionics and Biologically Relevant Models II; CMOS Realization of a 2-Layer CNN Universal Machine Chip -- CNN Based Color Constancy Algorithm -- Session Theory III; Improvement of the Method for Uncoupled Binary Input-Output CNN Template Decomposition -- Statistical Error Modeling of CNN-UM Architectures: The Binary Case -- Statistical Error Modeling of CNN-UM Architectures: The Grayscale Case -- Plenary Session; CNN and the Evolution of Complex Information Systems in Nature and Technology -- Future Visual Microsensors for Mini/Micro-UAV Applications -- CMOS Design of Cellular APAPs and FPAPAPs: An Overview -- MEMS, Microsystems and Nanosystems -- Session Learning I; On the Design Method of Cellular Neural Networks for Associative Memories Based on Generalized Eigenvalue Problem -- Multi-Template Training for Image Processing with Cellular Neural Networks -- Hardware-Oriented Algorithm for Associative Memories on Cellular Neural Networks -- Session Applications IV; Hysteresis Cellular Neural Networks for Solving Combinatorial Optimization Problems -- Texture Segmentation by the 64x64 CNN Chip -- Colour Space Transformation and Exact Colour Reproduction with CNN Technology -- Session CNN Development Systems (Poster); Image Processing Library for the Aladdin Visual Computer -- A New Design Method for the Neighborhood on Improving the CNN's Efficiency -- Application of Analogic CNN Algorithms in Telemedical Neuroradiology -- Composite Morphological Functions for DT-CNNs -- Teaching CNN and Learning by Using CNN -- Session Learning II; Novel Methods and Results in Training Universal Multi-Nested Neurons -- The Design of Ratio-Memory Cellular Neural Network (RMCNN) with Self-Feedback Template Weight for Pattern Learning and Recognition -- Supervised and Unsupervised ART-like Classifications of Binary Vectors on the CNN Universal Machine -- Non-Saturated Binary Image Learning and Recognition Using the Ratio-Memory Cellular Neural Network (RMCNN) -- Session Physical Implementations III; Design of IC Implementation of 16x16 CNN with Serial Parallel Input -- Analogue Weighted Median Filter Based on Cellular Neural Network for Standard Video Signal Processing -- Implementing Grayscale Morphological Operators with a Compact Ranked Order Extractor Circuit -- A Multimode Gray-Scale CMOS Optical Sensor for Visual Computers -- Test-Bed Board for 16x64 Stereo Vision CNN Chip -- Author Index.
• Texture Segmentation by the 64x64 CNN Chip -- Colour Space Transformation and Exact Colour Reproduction with CNN Technology -- Session CNN Development Systems (Poster) -- Image Processing Library for the Aladdin Visual Computer -- A New Design Method for the Neighborhood on Improving the CNN's Efficiency -- Application of Analogic CNN Algorithms in Telemedical Neuroradiology -- Composite Morphological Functions for DT-CNNs -- Teaching CNN and Learning by Using CNN -- Session Learning II -- Novel Methods and Results in Training Universal Multi-Nested Neurons -- The Design of Ratio-Memory Cellular Neural Network (RMCNN) with Self-Feedback Template Weight for Pattern Learning and Recognition -- Supervised and Unsupervised ART-like Classifications of Binary Vectors on the CNN Universal Machine -- Non-Saturated Binary Image Learning and Recognition Using the Ratio-Memory Cellular Neural Network (RMCNN) -- Session Physical Implementations III -- Design of IC Implementation of 16x16 CNN with Serial Parallel Input -- Analogue Weighted Median Filter Based on Cellular Neural Network for Standard Video Signal Processing -- Implementing Grayscale Morphological Operators with a Compact Ranked Order Extractor Circuit -- A Multimode Gray-Scale CMOS Optical Sensor for Visual Computers -- Test-Bed Board for 16x64 Stereo Vision CNN Chip -- Author Index
• Object-Oriented Image Analysis via Analogic CNN Algorithms - Part II: Image Synthesis and Consistency Observation -- A CNN Path Planning for a Mobile Robot in an Environment with Obstacles -- A CNN Based System to Blind Sources Separation of MEG Signals -- Delay-Driven Contrast Enhancement Using a Cellular Neural Network with State-Dependant Delay -- Plenary Session -- Time as Coding Space for Information Processing in the Cerebral Cortex -- Characterizing the Spatio-Temporal Dynamics of the Epileptogenic Process with Nonlinear EEG Analyses -- Session Bionics and Biologically Relevant Models I -- Analyzing Multidimensional Neural Activity via CNN-UM -- Basic Mammalian Retinal Effects on the Prototype Complex Cell CNN Universal Machine -- Prediction of Epileptic Seizures by CNN with Linear Weight Functions -- Biometric Authentication Based on Perceptual Resonance between CNN Emergent Patterns and Humans -- CNN Based Central Pattern Generators with Sensory Feedback -- Session Integrated Sensing and Processing -- Mobile Sensor-Actuator Networks: Opportunities and Challenges -- Visual Feedback by Using a CNN Chip Prototype System -- Multi-Target Tracking with Stored Program Adaptive CNN Universal Machines -- CNN-based 3D Thermal Modeling of the Soil for Antipersonnel Mine Detection -- PDE Based Histogram Modification with Embedded Morphological Processing of the Level-Sets -- Plenary Session -- Computational and Computer Complexity of Analogic Cellular Wave Computers -- Session Physical Implementations II -- Design of Min/Max Cellular Neural Networks (MMCNNS) in CMOS Technology -- Improved ARAM for PARIS, an Original Programmable Vision Chip -- An Accelerated Digital CNN-UM (CASTLE) Architecture by Using the Pipe-Line Technique -- PDE-DPCNN: A CNN Chip for Analogue Simulations of RD Equations -- Chaotic Phenomena in Quantum Cellular Neural Networks
• Intro -- CONTENTS -- FOREWORD -- Keynote Address -- The Origin of Complexity (presented, but paper not submitted) -- Plenary Session -- The Role of Field Coupling in Nano-Scale Cellular Nonlinear Networks -- Session Theory I -- On the Relationship Between CNNs and PDEs -- New Spatial-Temporal Patterns and the First Programmable On-Chip Bifurcation Test-Bed -- On Stability of Full Range and Polynomial Type CNNs -- A Study on Limit Cycles in Nearly Symmetric Cellular Neural Networks -- An Improved Global Stability Result for Cellular Neural Networks with Time Delay -- Session Applications I -- SC-CNNs for Chaotic Signals Generation -- Moving Object Tracking on Panoramic Images -- MPEG-4 Based Modifications for an CNN Segmentation Chip -- Watermarking for the Authentication of Video on CNN-UM -- An Analogic CNN-Algorithm of Pixel Level Snakes for Tracking and Surveillance Tasks -- Session Theory II -- On the Dynamics of a Class of Cellular Neural Networks -- mL-CNN: A CNN Model for Reaction-Diffusion Processes in m-Component Systems -- Emergence of Global Patterns in Connected Neural Networks -- Influence of System Non-Uniformity on Dynamic Phenomena in Arrays of Coupled Nonlinear Networks -- Boolean Design of Binary Initialized and Coupled CNN Image Processing Operators -- Session Physical Implementations I -- ACE16K: A 128x128 Focal Plane Analog Processor with Digital I/O. -- On the RTD Implementation of Simplicial Cellular Nonlinear Networks -- Programmable Optical CNN Implementation Based on the Template Pixels' Angular Coding -- Application Issues Of A Programmable Optical CNN Implementation -- Configurable Multi-Layer CNN-UM Emulator on FPGA -- Session Applications II (Poster) -- Object-Oriented Image Analysis via Analogic CNN Algorithms - Part I: Motion Estimation
• Session Applications III -- Fingerprint Image Enhacement Using CNN Gabor-Type Filters -- Obstacle Detection in Planar Worlds Using Cellular Neural Networks -- Potential Anomaly Separation Using Genetically Trained Multi-Level Cellular Neural Networks -- Fragile Watermarking and Unkeyed Hash Function Implementation for Image Authentication on CNN-UM -- Analogic Preprocessing and Segmentation Algorithms for Off-Line Handwriting Recognition -- Session Cellular and Sparsely Connected Dynamic Processor Systems (Poster) -- Nonlinear Dynamics and Propagation in Positive Feedback Comparators for A/D Converters -- Realization of Couplings in a Polynomial Type Mixed-Mode CNN -- A Cellular Fuzzy Associative Memory for Bidimensional Pattern Segmentation -- A/D and D/A Converters in a Mixed-Mode CNN -- Session Bionics and Biologically Relevant Models II -- CMOS Realization of a 2-Layer CNN Universal Machine Chip -- CNN Based Color Constancy Algorithm -- Session Theory III -- Improvement of the Method for Uncoupled Binary Input-Output CNN Template Decomposition -- Statistical Error Modeling of CNN-UM Architectures: The Binary Case -- Statistical Error Modeling of CNN-UM Architectures: The Grayscale Case -- Plenary Session -- CNN and the Evolution of Complex Information Systems in Nature and Technology -- Future Visual Microsensors for Mini/Micro-UAV Applications -- CMOS Design of Cellular APAPs and FPAPAPs: An Overview -- MEMS, Microsystems and Nanosystems -- Session Learning I -- On the Design Method of Cellular Neural Networks for Associative Memories Based on Generalized Eigenvalue Problem -- Multi-Template Training for Image Processing with Cellular Neural Networks -- Hardware-Oriented Algorithm for Associative Memories on Cellular Neural Networks -- Session Applications IV -- Hysteresis Cellular Neural Networks for Solving Combinatorial Optimization Problems