scholarly journals Zeroing neural network model for solving a generalized linear time-varying matrix equation

2021 ◽  
Vol 7 (2) ◽  
pp. 2266-2280
Author(s):  
Huamin Zhang ◽  
◽  
Hongcai Yin ◽  
Keyword(s):  
Neural Network ◽  
Matrix Equation ◽  
Noise Suppression ◽  
Linear Time ◽  
Network Models ◽  
Activation Function ◽  
Linear Matrix ◽  
Time Varying ◽  
Neural Network Models ◽  
Suppression Strategy

<abstract><p>The time-varying solution of a class generalized linear matrix equation with the transpose of an unknown matrix is discussed. The computation model is constructed and asymptotic convergence proof is given by using the zeroing neural network method. Using an activation function, the predefined-time convergence property and noise suppression strategy are discussed. Numerical examples are offered to illustrate the efficacy of the suggested zeroing neural network models.</p></abstract>

scholarly journals Prediction of Stress in Power Transformer Winding Conductors Using Artificial Neural Networks: Hyperparameter Analysis

Energies ◽  
2021 ◽  
Vol 14 (14) ◽  
pp. 4242
Author(s):  
Fausto Valencia ◽  
Hugo Arcos ◽  
Franklin Quilumba
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Power Transformer ◽  
Network Models ◽  
Activation Function ◽  
Neural Network Models ◽  
Transformer Winding ◽  
Artificial Neural ◽  
Femm Software

The purpose of this research is the evaluation of artificial neural network models in the prediction of stresses in a 400 MVA power transformer winding conductor caused by the circulation of fault currents. The models were compared considering the training, validation, and test data errors’ behavior. Different combinations of hyperparameters were analyzed based on the variation of architectures, optimizers, and activation functions. The data for the process was created from finite element simulations performed in the FEMM software. The design of the Artificial Neural Network was performed using the Keras framework. As a result, a model with one hidden layer was the best suited architecture for the problem at hand, with the optimizer Adam and the activation function ReLU. The final Artificial Neural Network model predictions were compared with the Finite Element Method results, showing good agreement but with a much shorter solution time.

Analysis of Fin-Tube Evaporator Performance With Limited Experimental Data Using Artificial Neural Networks

2000 ◽  
Author(s):  
Arturo Pacheco-Vega ◽  
Mihir Sen ◽  
Rodney L. McClain
Keyword(s):  
Neural Network ◽  
Heat Rate ◽  
Network Models ◽  
Activation Function ◽  
Operating Conditions ◽  
Training Data ◽  
Neural Network Models ◽  
The Neural Network ◽  
Artificial Neural ◽  
Fin Tube

Abstract In the current study we consider the problem of accuracy in heat rate estimations from artificial neural network models of heat exchangers used for refrigeration applications. The network configuration is of the feedforward type with a sigmoid activation function and a backpropagation algorithm. Limited experimental measurements from a manufacturer are used to show the capability of the neural network technique in modeling the heat transfer in these systems. Results from this exercise show that a well-trained network correlates the data with errors of the same order as the uncertainty of the measurements. It is also shown that the number and distribution of the training data are linked to the performance of the network when estimating the heat rates under different operating conditions, and that networks trained from few tests may give large errors. A methodology based on the cross-validation technique is presented to find regions where not enough data are available to construct a reliable neural network. The results from three tests show that the proposed methodology gives an upper bound of the estimated error in the heat rates.

A Method of Using Neural Networks and Inverse Kinematics for Machine Tools Error Estimation and Correction

1997 ◽  
Vol 119 (2) ◽  
pp. 247-254 ◽  
Author(s):  
J. Mou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Machine Tool ◽  
Inverse Kinematics ◽  
Network Models ◽  
Thermal Conditions ◽  
Depth Of Cut ◽  
Time Varying ◽  
Neural Network Models ◽  
Cutting Processes

A method using artificial neural networks and inverse kinematics for machine tool error correction is presented. A generalized error model is derived, by using rigid body kinematics, to describe the error motion between the cutting tool and workpiece at discrete temperature conditions. Neural network models are then built to track the time-varying machine tool errors at various thermal conditions. The output of the neural network models can be used to periodically modify, using inverse kinematics technique, the error model’s coefficients as the cutting processes proceeded. Thus, the time-varying positioning errors at other points within the designated workspace can be estimated. Experimental results show that the time-varying machine tool errors can be estimated and corrected with desired accuracy. The estimated errors resulted from the proposed methodology could be used to adjust the depth of cut on the finish pass, or correct the probing data for process-intermittent inspection to improve the accuracy of workpieces.

scholarly journals General Recurrent Neural Network for Solving Generalized Linear Matrix Equation

Complexity ◽  
2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Zhan Li ◽  
Hong Cheng ◽  
Hongliang Guo
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Recurrent Neural Network ◽  
Neural Network Model ◽  
Matrix Equation ◽  
Activation Function ◽  
Linear Matrix ◽  
Activation Functions ◽  
State Matrix ◽  
Linear Matrix Equation

This brief proposes a general framework of the nonlinear recurrent neural network for solving online the generalized linear matrix equation (GLME) with global convergence property. If the linear activation function is utilized, the neural state matrix of the nonlinear recurrent neural network can globally and exponentially converge to the unique theoretical solution of GLME. Additionally, as compared with the case of using the linear activation function, two specific types of nonlinear activation functions are proposed for the general nonlinear recurrent neural network model to achieve superior convergence. Illustrative examples are shown to demonstrate the efficacy of the general nonlinear recurrent neural network model and its superior convergence when activated by the aforementioned nonlinear activation functions.

scholarly journals Optimized Activation for Quantum-Inspired Self-supervised Neural Network based Fully Automated Brain MR Image Segmentation

2020 ◽  
Author(s):  
Debanjan Konar ◽  
Siddhartha Bhattacharyya ◽  
Bijaya Ketan Panigrahi
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Network Models ◽  
Activation Function ◽  
Medical Image Segmentation ◽  
Data Repository ◽  
Dynamic Susceptibility ◽  
Neural Network Models ◽  
Promising Alternative ◽  
Multi Level

<div>The slow-convergence problem degrades the segmentation performance of the recently proposed Quantum-Inspired Self-supervised Neural Network models owing to lack of suitable tailoring of the inter-connection weights. Hence, incorporation of quantum-inspired meta-heuristics in the Quantum-Inspired Self-supervised Neural Network models optimizes their hyper-parameters and inter-connection weights. This paper is aimed at proposing an optimized version of a Quantum-Inspired Self-supervised Neural Network (QIS-Net) model for optimal</div><div>segmentation of brain Magnetic Resonance (MR) Imaging. The suggested Optimized Quantum-Inspired Self-supervised Neural Network (Opti-QISNet) model resembles the architecture of QIS-Net and its operations are leveraged to obtain optimal segmentation outcome. The optimized activation function employed in the presented model is referred to as Quantum-Inspired Optimized Multi-Level Sigmoidal (Opti-QSig) activation. The Opti-QSig activation function is optimized by three quantum-inspired meta-heuristics with fifitness evaluation using Otsu’s multi-level thresholding. Rigorous experiments have been conducted on Dynamic Susceptibility Contrast (DSC) brain MR images from Nature data repository. The experimental outcomes show that the proposed self-supervised Opti-QISNet model offffers a promising alternative to the deeply supervised neural network based architectures (UNet and FCNNs) in medical image segmentation and outperforms our recently developed models QIBDS Net and QIS-Net.</div>

scholarly journals Delay-dependent asymptotic stability for neural networks with time-varying delays

2006 ◽  
Vol 2006 ◽  
pp. 1-25 ◽  
Author(s):  
Xiaofeng Liao ◽  
Xiaofan Yang ◽  
Wei Zhang
Keyword(s):  
Neural Network ◽  
Asymptotic Stability ◽  
Dynamical Behavior ◽  
Network Models ◽  
Time Varying ◽  
Stability Criteria ◽  
Neural Network Models ◽  
Neuron System ◽  
The Neural Network ◽  
Delay Dependent

We study the dynamical behavior of a class of neural network models with time-varying delays. By constructing suitable Lyapunov functionals, we obtain sufficient delay-dependent criteria to ensure local and global asymptotic stability of the equilibrium of the neural network. Our results are applied to a two-neuron system with delayed connections between neurons, and some novel asymptotic stability criteria are also derived. The obtained conditions are shown to be less conservative and restrictive than those reported in the known literature. Some numerical examples are included to demonstrate our results.

Sign in / Sign up

Export Citation Format

Share Document