Cellular neural network design using a learning algorithm

Zou, Fan; Schwarz, Sibylle; Nossek, Josef A.

doi:10.1109/cnna.1990.207509

Cited by 52 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relaxation method is a very simple algorithm for solving a system of linear inequalities iteratively [3]. Let us consider a system with n inequalities where Zc E R", i E R" and pc E R. Each constraint defines a closed half space P, = {i E RmlZi5+ pc 2 0) in the m-dimensional space.…”

Section: Relaxation Methodsmentioning

confidence: 99%

A learning algorithm for time-discrete cellular neural networks

Harrer¹,

Nossek²,

Zou³

1991

[Proceedings] 1991 IEEE International Joint Conference on Neural Networks

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Relaxation Methodsmentioning

confidence: 99%

A learning algorithm for time-discrete cellular neural networks

Harrer¹,

Nossek²,

Zou³

1991

[Proceedings] 1991 IEEE International Joint Conference on Neural Networks

Self Cite

View full text Add to dashboard Cite

show abstract

“…Depending on the gene specifying the behaviour of the CNN, the output image will be some transformation of the input and initial state images. Admittedly, it is less than straightforward to design a CNN gene for such a task; however, as we mentioned earlier, evolutionary computation can be used to discover the appropriate CNN genes that implement the desired algorithm [8,13,19,23,30].…”

Section: Universality Of Cnn Algorithmsmentioning

confidence: 98%

“…Output Input This vector is usually called a CNN gene, owing to the fact that evolutionary algorithms can be employed to find these parameters [8,13,19,23,30].…”

Section: Cnn Genesmentioning

confidence: 99%

CNN-based language and interpreter for image processing on GPUs

Dolan

DeSouza

2011

International Journal of Parallel, Emergent and Distributed Sys

View full text Add to dashboard Cite

The inherent massive parallelism of cellular neural networks (CNNs) makes them an ideal computational platform for kernel-based algorithms and image processing. General-purpose graphics processing units (GPUs) provide similar massive parallelism, but it can be difficult to design algorithms to make optimal use of the hardware. In this paper, we present a programming environment based on CNNs that can run on GPUs, multi-core CPUs or simply simulated in software. The platform offers a simplified view of massively parallel computation which remains universal and reasonably efficient. An image processing library with visualisation software has been developed using the abstraction to showcase the flexibility and power of cellular computation on GPUs. A simple virtual machine and language is presented to manipulate images using the library for single-core, multi-core and GPU backends.

show abstract

“…transconductance of linear current sources {A{i,j', k, 1) and k, /)), the bias current (/), the resistances (R^ and Ry), capacitance C and the radius of the direct interactions between cells (r). El ements mentioned above are called CNN parameters and how to choose these parameters to achieve a desired transformation is currently still an active re search problem [25], [26]. Some application possibilities like noise-reduction and edge detection are mentioned in Chapter 4, and others can be found in the references [12], [17]- [20].…”

Section: A P P Lication To Im Age P Rocessin Gmentioning

confidence: 99%