A recurrent dynamic neural network for noisy signal representation

Zohdy, Mohamed; Karam, M.; Zohdy, Hoda S. Abdel-Aty

doi:10.1016/s0925-2312(97)00043-x

Cited by 17 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6) Model (1) often represents biological systems, which reflects the survival and perdition of species. In contrast, (4) stems from engineering applications, and in a similar manner to Hopfield neural network model, they can be used in fields, such as optimization, decision making and learning [91], [208], [252], [253], and signal processing [327]. The similarities between ( 1) and ( 4) are as follows: 1) the model structure in mathematical description is the same and 2) the symmetry requirements of the interconnection matrices are the same in the early days of neural network stability theory.…”

Section: Stability Problems For Two Classes Of Cohen-grossberg Neural...mentioning

confidence: 99%

A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks

Zhang¹,

Wang²,

Liu

2014

IEEE Trans. Neural Netw. Learning Syst.

568

151

View full text Add to dashboard Cite

Stability problems of continuous-time recurrent neural networks have been extensively studied, and many papers have been published in the literature. The purpose of this paper is to provide a comprehensive review of the research on stability of continuous-time recurrent neural networks, including Hopfield neural networks, Cohen-Grossberg neural networks, and related models. Since time delay is inevitable in practice, stability results of recurrent neural networks with different classes of time delays are reviewed in detail. For the case of delay-dependent stability, the results on how to deal with the constant/variable delay in recurrent neural networks are summarized. The relationship among stability results in different forms, such as algebraic inequality forms, M-matrix forms, linear matrix inequality forms, and Lyapunov diagonal stability forms, is discussed and compared. Some necessary and sufficient stability conditions for recurrent neural networks without time delays are also discussed. Concluding remarks and future directions of stability analysis of recurrent neural networks are given.

show abstract

Section: Stability Problems For Two Classes Of Cohen-grossberg Neural...mentioning

confidence: 99%

A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks

Zhang¹,

Wang²,

Liu

2014

IEEE Trans. Neural Netw. Learning Syst.

568

151

View full text Add to dashboard Cite

show abstract

“…Supervised Recurrent Dynamic Neural Networks (RDNNs) that require knowledge of the system model have been studied and can be used to solve non-linear equations, representation of noisy signals as well as for static related applications [8][9][10]. RDNN with wavelet as a basis function provides a flexible and intelligent approach for defect tracking in systems and related applications [6,11].…”

Section: Wavelet Basis Rdnnmentioning

confidence: 99%

Three Bio-Inspired Approaches to Telecommunications Defect-Tracking and Reliability-Estimation

Abdel-Aty-Zohdy

Sherif

Smiarowski

2006

2006 49th IEEE International Midwest Symposium on Circuits and Systems

View full text Add to dashboard Cite

Three alternative bio-inspired approaches are proposed to investigate telecommunication system reliability and defect tracking. They employ a recent model for the failure discovery in the associated system software. These are: Half-Sibling and A Clone (HSAC) Genetic Algorithm; a Recurrent Dynamic Neural Network (RDNN) requiring parametric adjustments and using wavelets as basis; another RDNN with Adaptive parameters to incoming stream of input data, such that the error in failure intensity is minimized, subject to the model constraints. Each approach aims to improve speed of convergence, reliability, noise tolerance, and suitability for hardware implementation. Simulation results seem to favor the ARDNN since it iterates (about 10) on the shape of the wavelet basis and provide adequate recovery of the data in the form of piecewise linear differential'.

show abstract

“…2, intelligent bio-inspired detection (cognitive) means bio-inspired designs will be incorporating neural nets. Fig 2. indicates that to develop a bio-inspired/intelligent signal-processing system for chemical and bio-chemical sensing by developing and implementing four sequential stages for neuroSlice cognitive signal processing architecture [12][13][14][15][16] The NeuroSlice architecture has many components, loosely coupled together. The components are designed to work together, or to work separately.…”

Section: Introductionmentioning

confidence: 99%

Next-generation advances in cognitive processing using spiking neural networks for biochemical sensing, radar and rapid HDL

Abdel-Aty-Zohdy

Allen

2009

Proceedings of the IEEE 2009 National Aerospace &Amp; Electronics Conference (NAECON)

View full text Add to dashboard Cite

This invited plenary paper introduces a novel spiking neural network methodology, and applies it to an odorant learning, medical and radar detection applications. Rapid HDL is introduced as a 15 minute rapid prototyping approach, where real-time implementations will be demoed on FPGAs. The spiketime dependent plasticity can support coding schemes that are based on spatio-temporal spike patterns. Spiking (or pulsed) neural networks (SNNs) are models which explicitly take into account the timing of inputs. The network input and output are usually represented as series of spikes (delta function or more complex shapes). Plasticity SNNs have an advantage of being able to recurrently process information. Spike-time dependent plasticity can enhance signal transmission by selectively strengthening synaptic connections that transmit precisely timed spikes at the expense of those synapses that transmit poorly timed spikes.

show abstract

A recurrent dynamic neural network for noisy signal representation

Cited by 17 publications

References 15 publications

A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks

A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks

Three Bio-Inspired Approaches to Telecommunications Defect-Tracking and Reliability-Estimation

Next-generation advances in cognitive processing using spiking neural networks for biochemical sensing, radar and rapid HDL

Contact Info

Product

Resources

About