High Degree Multivariate Fuzzy Approximation by Neural Network Operators Using the Error Function

2015 ◽  
pp. 465-496 ◽  
Author(s):  
George A. Anastassiou
Keyword(s):  
Neural Network ◽  
Error Function ◽  
Fuzzy Approximation ◽  
High Degree

scholarly journals Cytoskeleton and Membrane Organization at Axon Branches

2021 ◽  
Vol 9 ◽  
Author(s):  
Satish Bodakuntla ◽  
Hana Nedozralova ◽  
Nirakar Basnet ◽  
Naoko Mizuno
Keyword(s):  
Neural Network ◽  
Energy Production ◽  
Network Formation ◽  
Local System ◽  
Membrane Remodeling ◽  
Axon Branching ◽  
Cellular Functions ◽  
Branch Formation ◽  
High Degree ◽  
Critical Process

Axon branching is a critical process ensuring a high degree of interconnectivity for neural network formation. As branching occurs at sites distant from the soma, it is necessary that axons have a local system to dynamically control and regulate axonal growth. This machinery depends on the orchestration of cellular functions such as cytoskeleton, subcellular transport, energy production, protein- and membrane synthesis that are adapted for branch formation. Compared to the axon shaft, branching sites show a distinct and dynamic arrangement of cytoskeleton components, endoplasmic reticulum and mitochondria. This review discusses the regulation of axon branching in the context of cytoskeleton and membrane remodeling.

Artificial Intelligence in Aviation Industries

2020 ◽  
pp. 1-35
Author(s):  
Tetiana Shmelova ◽  
Arnold Sterenharz ◽  
Serge Dolgikh
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Decision Making ◽  
Unmanned Aircraft ◽  
Innovative Technology ◽  
Sociotechnical System ◽  
Air Traffic Controllers ◽  
High Degree ◽  
Difficult Situations

This chapter presents opportunities to use Artificial Intelligence (AI) in aviation and aerospace industries. The AI used an innovative technology for improving the effectiveness of building aviation systems in each stage of the lifecycle for enhancing the security of aviation systems and the characteristic ability to learn, improve, and predict difficult situations. The AI is presented in Air Navigation Sociotechnical system (ANSTS) because the activity of ANSTS, is accompanied by a high degree of risk of causing catastrophic outcomes. The operator's models of decision making in AI systems are presented such as Expert Systems, Decision Support Systems for pilots of manned and unmanned aircraft, air traffic controllers, engineers, etc. The quality of operator's decisions depends on the development and use of innovative technology of AI and related fields (Big Data, Data Mining, Multicriteria Decision Analysis, Collaboration Decision Making, Blockchain, Artificial Neural Network, etc.).

scholarly journals Evaluation of Pre-Trained Convolutional Neural Network Models for Object Recognition

2018 ◽  
Vol 7 (3.15) ◽  
pp. 95 ◽  
Author(s):  
M Zabir ◽  
N Fazira ◽  
Zaidah Ibrahim ◽  
Nurbaity Sabri
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Visual Recognition ◽  
Error Function ◽  
Network Models ◽  
Neural Network Models ◽  
California Institute Of Technology ◽  
Institute Of Technology ◽  
Similar Accuracy

This paper aims to evaluate the accuracy performance of pre-trained Convolutional Neural Network (CNN) models, namely AlexNet and GoogLeNet accompanied by one custom CNN. AlexNet and GoogLeNet have been proven for their good capabilities as these network models had entered ImageNet Large Scale Visual Recognition Challenge (ILSVRC) and produce relatively good results. The evaluation results in this research are based on the accuracy, loss and time taken of the training and validation processes. The dataset used is Caltech101 by California Institute of Technology (Caltech) that contains 101 object categories. The result reveals that custom CNN architecture produces 91.05% accuracy whereas AlexNet and GoogLeNet achieve similar accuracy which is 99.65%. GoogLeNet consistency arrives at an early training stage and provides minimum error function compared to the other two models. 

Artificial Neural Network Learning of Nonstationary Behavior in Time Series

2003 ◽  
Vol 13 (02) ◽  
pp. 103-109 ◽  
Author(s):  
María I. Széliga ◽  
Pablo F. Verdes ◽  
Pablo M. Granitto ◽  
H. Alejandro Ceccatto
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Error Function ◽  
Input Parameter ◽  
Input Unit ◽  
Validation Data ◽  
Neural Network Learning ◽  
Secular Evolution ◽  
Artificial Neural

We refine and complement a previously-proposed artificial neural network method for learning hidden signals forcing nonstationary behavior in time series. The method adds an extra input unit to the network and feeds it with the proposed profile for the unknown perturbing signal. The correct time evolution of this new input parameter is learned simultaneously with the intrinsic stationary dynamics underlying the series, which is accomplished by minimizing a suitably-defined error function for the training process. We incorporate here the use of validation data, held out from the training set, to accurately determine the optimal value of a hyperparameter required by the method. Furthermore, we evaluate this algorithm in a controlled situation and show that it outperforms other existing methods in the literature. Finally, we discuss a preliminary application to the real-world sunspot time series and link the obtained hidden perturbing signal to the secular evolution of the solar magnetic field.

The Reconstruction of Significant Wave Height Time Series by Using a Neural Network Approach

2004 ◽  
Vol 126 (3) ◽  
pp. 213-219 ◽  
Author(s):  
Felice Arena ◽  
Silvia Puca
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Wave Height ◽  
Significant Wave Height ◽  
Error Function ◽  
Neural Network Approach ◽  
Significant Wave ◽  
Time Periods ◽  
Weighted Error ◽  
Storm Model

A Multivariate Neural Network (MNN) algorithm is proposed for the reconstruction of significant wave height time series, without any increase of the error of the MNN output with the number of modelled data. The algorithm uses a weighted error function during the learning phase, to improve the modelling of the higher significant wave height. The ability of the MNN to reconstruct sea storms is tested by applying the equivalent triangular storm model. Finally an application to the NOAA buoys moored off California shows a good performance of the MNN algorithm, both during sea storms and calm time periods.

Sign in / Sign up

Export Citation Format

Share Document