Sigma–delta cellular neural network for 2D modulation

Aomori, Hisashi; Otake, Tsuyoshi; Takahashi, Nobuaki; Tanaka, Mamoru

doi:10.1016/j.neunet.2007.12.020

Cited by 17 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sigma-delta cellular neural network (SD-CNN) [2] is a novel framework of spatial domain sigma-delta modulation utilizing neuro dynamics. The basic concepts behind the SD-CNN are the sigma-delta modulation and cellular neural network (CNN) [3].…”

Section: Introductionmentioning

confidence: 99%

An oversampling 2D sigma-delta converter by cellular neural networks

Aomori

Otake

Takahashi

et al. 2010

Proceedings of 2010 IEEE International Symposium on Circuits and Systems

Self Cite

View full text Add to dashboard Cite

The sigma-delta cellular neural network (SD-CNN) is a novel framework of spatial domain sigma-delta modulation utilizing neuro dynamics. Also, it has signal reconstruction and noise shaping characteristics that are important sigma-delta properties. Although the noise shaping effect with the oversampling technique plays very important role for drastic quantization noise reduction in binary digital sequences, the conventional SD-CNN could not use it effectively since it can be thought that the time-domain and spatial-domain oversampling are effective for the SD-CNN. In this paper, a novel SD-CNN with the oversampling technique for an analogue DC input is proposed. Experimental results of various standard test images in several oversampling ratios suggest that the proposed oversampling SD-CNN has an excellent AD and DA performance.

show abstract

Section: Introductionmentioning

confidence: 99%

An oversampling 2D sigma-delta converter by cellular neural networks

Aomori

Otake

Takahashi

et al. 2010

Proceedings of 2010 IEEE International Symposium on Circuits and Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Cellular network can convert the multi-bit image into an optimal binary halftone image. This significant characteristic of a cellular network suggests the possibility of a spatial domain sigma-delta modulation [5]. The proposed system can be treated as a very large-scale and super-parallel sigma-delta modulator.…”

Section: Cellular Neural Networkmentioning

confidence: 99%

Hopfield Networks, Simulated Annealing, and Chaotic Neural Networks

Du¹,

Swamy

2013

Neural Networks and Statistical Learning

View full text Add to dashboard Cite

The Hopfield model [27,28] is the most popular dynamic model. It is biologically plausible since it functions like the human retina [36]. It is a fully interconnected recurrent network with J McCulloch-Pitts neurons. The Hopfield model is usually represented by using a J -J layered architecture, as illustrated in Fig. 6.1. The input layer only collects and distributes feedback signals from the output layer. The network has a symmetric architecture with a symmetric zero-diagonal real weight matrix, that is, w i j = w ji and w ii = 0. Each neuron in the second layer sums the weighted inputs from all the other neurons to calculate its current net activation net i , then applies an activation function to net i and broadcasts the result along the connections to all the other neurons. In the figure, w ii = 0 is represented by a dashed line; φ(·) and θ are, respectively, a vector comprising the activation functions for all the neurons and a vector comprising the biases for all the neurons.The Hopfield model operates in an unsupervised manner. The dynamics of the network are described by a system of nonlinear ordinary differential equations. The discrete form of the dynamics is defined by1)where net i is the weighted net input of the ith neuron, x i (t) is the output of the ith neuron, θ i is a bias to the neuron, and φ(·) is the sigmoidal function.

show abstract

“…16 Application of different artificial neural network (ANN) topologies, [17][18][19][20][21] simulated annealing, 22 multipath tree coding, 16 direct binary search, 23 etc. have been reported in this regard.…”

Section: Introductionmentioning

confidence: 99%

“…Different architectures of ANN have been employed to solve the shortcomings of classical digital halftoning techniques as well. [17][18][19][20][21]24 RNN is one of the developments of ANN that offers temporal memory 25 in terms of recurrent links between the nodes of one layer and one of its previous layers. 26 The presence of context layer distinguishes recurrent neural network (RNN) architectures from conventional feed forward multilayer perceptron models.…”

Section: Introductionmentioning

confidence: 99%

A temporal memory-based ordered dithering using recurrent neural network

Chatterjee

Tudu

Paul

2013

The Imaging Science Journal

View full text Add to dashboard Cite

Ordered dither is a popular digital halftoning technique used for bi-level displays. Despite its popularity, this technique results in two major problems e.g. objectionable periodic patterns and false contouring. This paper presents a temporal memory-based approach for ordered dithering. Digital halftoning has been considered as an optimisation problem. The temporal memory of recurrent neural network (RNN) has been employed to generate optimised halftone patterns. The temporal memory of RNN is used to retain association between pixels under processing and pixels already processed for generating the screen matrix. The human visual system (HVS) characteristics have been involved in cost function formulation. The proposed framework has been investigated with two most commonly practiced architectures of RNN, namely, Elman RNN and Jordan RNN. The results obtained using both the architectures have been presented pictorially. The results have also been evaluated against quality evaluation metrics such as peak signal-to-noise ratio (PSNR), universal quality index (UQI) and structural similarity index measure (SSIM). The results show that the proposed method may be potentially useful in the field of digital halftoning.

show abstract

Sigma–delta cellular neural network for 2D modulation

Cited by 17 publications

References 20 publications

An oversampling 2D sigma-delta converter by cellular neural networks

An oversampling 2D sigma-delta converter by cellular neural networks

Hopfield Networks, Simulated Annealing, and Chaotic Neural Networks

A temporal memory-based ordered dithering using recurrent neural network

Contact Info

Product

Resources

About