On the Impact of Energy-Accuracy Tradeoff in a Digital Cellular Neural Network for Image Processing

Kung, Jaeha; Kim, Duck-Hwan; Mukhopadhyay, Saibal

doi:10.1109/tcad.2015.2406853

Cited by 26 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here the we standardize and reshape the images to fit into the network. The Number of neurons in the hidden layer is considered to be 10 and the learning rate for input layer =0.4 and the learning rate for the output layer =0.3 [9].…”

Section: Neural Network Training Processmentioning

confidence: 99%

An Image Compression Based Technique to Watermark a Neural Network

Kavitha*,

Eranna,

Giriprasad

2020

IJITEE

View full text Add to dashboard Cite

While neural networks have made considerable progress in the area of digital representation, training of neural models requires an enormous data and time. It is well known that the use of trained models as initial weights often leads in less training error than un-pre-trained neural networks. We propose in this paper a digital watermarking system for neural networks. We formulate a new challenge: the integration of watermarks into neural networks through discrete cosine transform (DCT) based approach. For discrete wavelet transform (DWT)-based digital image watermarking algorithms, additional performance enhancements could be obtained by combining DWT with DCT. Throughout the neural networks, we also describe specifications, embedded conditions, and attack forms of watermarking. The technique presented here does not affect the network performance in which a watermark is positioned as the watermark is embedded while the host network is being trained. Finally, we perform detailed image data experiments to demonstrate the potential of neural networks watermarking as the basis for this research attempt.

show abstract

Section: Neural Network Training Processmentioning

confidence: 99%

An Image Compression Based Technique to Watermark a Neural Network

Kavitha*,

Eranna,

Giriprasad

2020

IJITEE

View full text Add to dashboard Cite

show abstract

“…Learning efficiency and structural sparsification are two important issues in the study and application of neural networks. The learning efficiency is mainly concerned with the choice of learning method so as to achieve good learning accuracy for the training samples and generalization (test) accuracy for the untrained samples [1][2][3][4][5]. The aim of structural sparsification is to use less numbers of nodes and connections (weights) without causing damage to the learning efficiency [6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Binary Output Layer of Feedforward Neural Networks for Solving Multi-Class Classification Problems

Yang

Zhang

2019

IEEE Access

View full text Add to dashboard Cite

Considered in this short note is the design of output layer nodes of feedforward neural networks for solving multi-class classification problems with r (r ≥ 3) classes of samples. The common and conventional setting of output layer, called "one-to-one approach" in this paper, is as follows: The output layer contains r output nodes corresponding to the r classes. And for an input sample of the i-th class (1 ≤ i ≤ r), the ideal output is 1 for the i-th output node, and 0 for all the other output nodes. We propose in this paper a new "binary approach": Suppose 2 q−1 < r ≤ 2 q with q ≥ 2, then we let the output layer contain q output nodes, and let the ideal outputs for the r classes be designed in a binary manner. Numerical experiments carried out in this paper show that our binary approach does equally good job as, but uses less output nodes than, the traditional one-to-one approach.

show abstract

“…[1][2][3][4][5] Neural networks usually possess the characteristics of adaptivity, nonlinearity, parallelism and distributed storage, which can be used to solve the complicated problems that can not be solved by other approaches. [6][7][8][9] Specifically, the applications of neural networks including (but not limited to) the pattern classification, [10,11] deep learning, [12,13] approximation and prediction, [14,15] image processing, [16,17] machine learning, [18,19] optimization and computation, [20,21] complex system control [22][23][24] (including the robot system control). [25,26] Due to the extensive and significant applications of neu-ral networks, the development and investigation of neural networks have become common and heated topics for the researchers in biology, mathematics, physics, and computer science.…”

Section: Introductionmentioning

confidence: 99%

A Review on Neural Dynamics for Robot Autonomy

Chen

2018

IJRC

View full text Add to dashboard Cite

Exploiting neural networks to solve control problems of robots is becoming commonly and effectively in academia and engineering. Due to the remarkable features like distributed storage, parallelism, easy implementation by hardware, adaptive self-learning capability, and free of off-line training, the solutions of neural networks break the bottlenecks of serial-processing strategies and methods, and serve as significant alternatives for robotic engineers and researchers. Especially, various types and branches of recurrent neural networks (RNNs) have been sequentially developed since the seminal works by Hopfield and Tank. Successively, many classes and branches of RNNs such as primal-dual neural networks (PDNNs), zeroing neural networks (ZNNs) and gradient neural networks (GNNs) are proposed, investigated, developed and applied to the robot autonomy. The objective of this paper is to present a comprehensive review of the research on neural networks (especially RNNs) for control problems solving of different kinds of robots. Specifically, the state-of-the-art research of RNNs, PDNNs, ZNNs and GNNs in different robot control problems solving are detailedly revisited and reported. The readers can readily find many effective and valuable solutions on the basis of neural networks for the robot autonomy in this paper.

show abstract

On the Impact of Energy-Accuracy Tradeoff in a Digital Cellular Neural Network for Image Processing

Cited by 26 publications

References 22 publications

An Image Compression Based Technique to Watermark a Neural Network

An Image Compression Based Technique to Watermark a Neural Network

Binary Output Layer of Feedforward Neural Networks for Solving Multi-Class Classification Problems

A Review on Neural Dynamics for Robot Autonomy

Contact Info

Product

Resources

About