Delayed Standard Neural Network Models for the Stability Analysis of Recurrent Neural Networks

2006 ◽  
Vol 2 (1) ◽  
Author(s):  
Meiqin Liu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Stability Analysis ◽  
Recurrent Neural Networks ◽  
Network Models ◽  
Neural Network Models ◽  
The Stability

scholarly journals Weather Nowcasting Using Deep Learning Techniques

2021 ◽  
Author(s):  
Makhamisa Senekane ◽  
Mhlambululi Mafu ◽  
Molibeli Benedict Taele
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Weather Forecasting ◽  
Network Models ◽  
Short Term ◽  
Neural Network Models ◽  
Precipitation Forecasting ◽  
Learning Techniques

Weather variations play a significant role in peoples’ short-term, medium-term or long-term planning. Therefore, understanding of weather patterns has become very important in decision making. Short-term weather forecasting (nowcasting) involves the prediction of weather over a short period of time; typically few hours. Different techniques have been proposed for short-term weather forecasting. Traditional techniques used for nowcasting are highly parametric, and hence complex. Recently, there has been a shift towards the use of artificial intelligence techniques for weather nowcasting. These include the use of machine learning techniques such as artificial neural networks. In this chapter, we report the use of deep learning techniques for weather nowcasting. Deep learning techniques were tested on meteorological data. Three deep learning techniques, namely multilayer perceptron, Elman recurrent neural networks and Jordan recurrent neural networks, were used in this work. Multilayer perceptron models achieved 91 and 75% accuracies for sunshine forecasting and precipitation forecasting respectively, Elman recurrent neural network models achieved accuracies of 96 and 97% for sunshine and precipitation forecasting respectively, while Jordan recurrent neural network models achieved accuracies of 97 and 97% for sunshine and precipitation nowcasting respectively. The results obtained underline the utility of using deep learning for weather nowcasting.

scholarly journals Stability Analysis of Neural Network Models in Engineering Design

2020 ◽  
Vol 9 (3) ◽  
pp. 1862-1866
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Stability Analysis ◽  
Engineering Design ◽  
Network Models ◽  
Control Problems ◽  
Neural Network Models ◽  
Optimization And Control ◽  
Efficient Criteria ◽  
And Control

In this paper neural networks applications in engineering design are discussed. The question for stability of their steady states is also considered. Some new efficient criteria are proposed. Since neural networks are relevant systems applied in various engineering design tasks, including many optimization and control problems, the results can be useful in design of such systems of diverse interest.

scholarly journals Design and Practical Stability of a New Class of Impulsive Fractional-Like Neural Networks

Entropy ◽  
2020 ◽  
Vol 22 (3) ◽  
pp. 337 ◽  
Author(s):  
Gani Stamov ◽  
Ivanka Stamova ◽  
Anatoliy Martynyuk ◽  
Trayan Stamov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Practical Stability ◽  
Bidirectional Associative Memory ◽  
Neural Network Models ◽  
New Class ◽  
New Type ◽  
Bam Neural Network ◽  
The Stability

In this paper, a new class of impulsive neural networks with fractional-like derivatives is defined, and the practical stability properties of the solutions are investigated. The stability analysis exploits a new type of Lyapunov-like functions and their derivatives. Furthermore, the obtained results are applied to a bidirectional associative memory (BAM) neural network model with fractional-like derivatives. Some new results for the introduced neural network models with uncertain values of the parameters are also obtained.

scholarly journals Neural Networks in Engineering Design: Robust Practical Stability Analysis

2021 ◽  
Vol 21 (4) ◽  
pp. 3-14
Author(s):  
Trayan Stamov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Stability Analysis ◽  
Engineering Design ◽  
Network Models ◽  
Practical Stability ◽  
Design Stage ◽  
Neural Network Models ◽  
Network Systems ◽  
Engineering Design Problems

Abstract In recent years, we are witnessing artificial intelligence being deployed on embedded platforms in our everyday life, including engineering design practice problems starting from early stage design ideas to the final decision. One of the most challenging problems is related to the design and implementation of neural networks in engineering design tasks. The successful design and practical applications of neural network models depend on their qualitative properties. Elaborating efficient stability is known to be of a high importance. Also, different stability notions are applied for differently behaving models. In addition, uncertainties are ubiquitous in neural network systems, and may result in performance degradation, hazards or system damage. Driven by practical needs and theoretical challenges, the rigorous handling of uncertainties in the neural network design stage is an essential research topic. In this research, the concept of robust practical stability is introduced for generalized discrete neural network models under uncertainties applied in engineering design. A robust practical stability analysis is offered using the Lyapunov function method. Since practical stability concept is more appropriate for engineering applications, the obtained results can be of a practical significance to numerous engineering design problems of diverse interest.

scholarly journals Opening the black box of neural networks: methods for interpreting neural network models in clinical applications

2018 ◽  
Vol 6 (11) ◽  
pp. 216-216 ◽  
Author(s):  
Zhongheng Zhang ◽  
◽  
Marcus W. Beck ◽  
David A. Winkler ◽  
Bin Huang ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Black Box ◽  
Clinical Applications ◽  
Neural Network Models

scholarly journals Robotic grasp detection using a novel two-stage approach

2021 ◽  
Vol 1 (1) ◽  
pp. 19-29
Author(s):  
Zhe Chu ◽  
Mengkai Hu ◽  
Xiangyu Chen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
Particle Swarm Optimizer ◽  
Neural Network Models ◽  
Two Stage ◽  
The Neural Network ◽  
End To End ◽  
Small Change ◽  
Robotic Grasp

Recently, deep learning has been successfully applied to robotic grasp detection. Based on convolutional neural networks (CNNs), there have been lots of end-to-end detection approaches. But end-to-end approaches have strict requirements for the dataset used for training the neural network models and it’s hard to achieve in practical use. Therefore, we proposed a two-stage approach using particle swarm optimizer (PSO) candidate estimator and CNN to detect the most likely grasp. Our approach achieved an accuracy of 92.8% on the Cornell Grasp Dataset, which leaped into the front ranks of the existing approaches and is able to run at real-time speeds. After a small change of the approach, we can predict multiple grasps per object in the meantime so that an object can be grasped in a variety of ways.

Sign in / Sign up

Export Citation Format

Share Document