Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 13 of 13 for “"Cellular neural network"”.
-
Cellular neural network virtual machine for graphics hardware with applications in image processing
The inherent massive parallelism of cellular neural networks makes them an ideal computational platform for kernel-based algorithms and image processing. General-purpose GPUs provide similar massive parallelism, but it can be difficult to design algorithms to make optimal use of the hardware. The …
-
Bio-Inspired Distributed Constrained Optimization Technique and its Application in Dynamic Thermal Management
The stomatal network in plants is a well-characterized biological system that hypothetically solves the constrained optimization problem of maximizing CO2 uptake from the air while constraining evaporative water loss during the process of photosynthesis. There are numerous such constrained …
-
Internal symmetry networks for image processing
Internal Symmetry Networks are a recently developed class of Cellular Neural Network inspired by the phenomenon of internal symmetry in quantum physics. Their hidden unit activations are acted on non-trivially by the dihedral group of symmetries of the square. Here, we extend Internal Symmetry …
-
Memristor-based and time-delay nonlinear circuits
… much attention recently: time delay system, Cellular Neural Network and memristive system. In this thesis we investigate how the properties of these nonlinear systems can be efficiently exploited to build novel chaotic systems and to observe novel complex phenomena.
-
A connectionist approach to autonomous robotic navigation
… processed in retinal patch size elements by a cellular neural network. This network is designed to detect obstacle existence for each patch segment based on an invariant feature of range discontinuity. Obstacle information is then mapped in binary format, indicating the traversable state of the …
-
Ultra low power non-Boolean computing with tunneling field-effect-transistors
… field-effect-transistors (TFET) and large scale cellular neural network (CNN). Particularly, low ON/OFF current of Si channel TFET, while not promising for digital applications, is found suitable for large scale CNN. By collective computing, large scale CNN mitigates on-current deficiencies of Si …
-
Memristor based neural networks: Feasibility, theories and approaches
Memristor-based neural networks refer to the utilisation of memristors, the newly emerged nanoscale devices, in building neural networks. The memristor was first postulated by Leon Chua in 1971 as the fourth fundamental passive circuit element and experimentally validated by one of HP labs in 2008. …
-
Co-Design of Algorithms and Architectures for Embedded, Event-Based Machine Perception
… through the modeling of a spike-based Cellular Neural Network processing element. Next, I devised a series of micro-architectures and digital readout schemes to interface with silicon retinas and realize localized processing and decoding. These included Field Programmable Gate Array …
-
Confinement effects in shallow water jets
… of the PIV images and filtering outliers using a cellular neural network with a variable threshold, the statistical quantities such as mean velocities, turbulence intensities, Reynolds shear stress, centreline velocity decay, centreline turbulence intensities, and spread rate were obtained. The …
-
On Hardware Implementation of Discrete-Time Cellular Neural Networks
Cellular Neural Networks are characterized by simplicity of operation. The network consists of a large number of nonlinear processing units; called cells; that are equally spread in the space. Each cell has a simple function (sequence of multiply-add followed by a single discrimination) that takes …
-
Apprendimento di modelli per reti cellulari non lineari (CNN): tecniche e applicazioni
… dei coefficienti del modello per le reti neurali cellulari (CNN) applicati a varie attività di elaborazione delle immagini. Attraverso l'apprendimento supervisionato, oppure tramite l'elaborazione delle immagini tecniche o schizzi manuali, l'algoritmo RWC ha ridotto al minimo l'errore con …