Preferred Language
Articles
/
wBfmQo8BVTCNdQwCRmeE
On the Greedy Ridge Function Neural Networks for Approximation Multidimensional Functions
...Show More Authors

The aim of this paper is to approximate multidimensional functions f∈C(R^s) by developing a new type of Feedforward neural networks (FFNS) which we called it Greedy ridge function neural networks (GRGFNNS). Also, we introduce a modification to the greedy algorithm which is used to train the greedy ridge function neural networks. An error bound are introduced in Sobolov space. Finally, a comparison was made between the three algorithms (modified greedy algorithm, Backpropagation algorithm and the result in [1]).

Preview PDF
Quick Preview PDF
Publication Date
Fri Jun 01 2007
Journal Name
Journal Of Al-nahrain University Science
ON THE GREEDY RADIAL BASIS FUNCTION NEURAL NETWORKS FOR APPROXIMATION MULTIDIMENSIONAL FUNCTIONS
...Show More Authors

The aim of this paper is to approximate multidimensional functions by using the type of Feedforward neural networks (FFNNs) which is called Greedy radial basis function neural networks (GRBFNNs). Also, we introduce a modification to the greedy algorithm which is used to train the greedy radial basis function neural networks. An error bound are introduced in Sobolev space. Finally, a comparison was made between the three algorithms (modified greedy algorithm, Backpropagation algorithm and the result is published in [16]).

View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Apr 01 2018
Journal Name
Journal Of Economics And Administrative Sciences
Estimate Kernel Ridge Regression Function in Multiple Regression
...Show More Authors

             In general, researchers and statisticians in particular have been usually used non-parametric regression models when the parametric methods failed to fulfillment their aim to analyze the models  precisely. In this case the parametic methods are useless so they turn to non-parametric methods for its easiness in programming. Non-parametric methods can also used to assume the parametric regression model for subsequent use. Moreover, as an advantage of using non-parametric methods is to solve the problem of Multi-Colinearity between explanatory variables combined with nonlinear data. This problem can be solved by using kernel ridge regression which depend o

... Show More
View Publication Preview PDF
Crossref
Publication Date
Wed Mar 10 2021
Journal Name
Baghdad Science Journal
On Training Of Feed Forward Neural Networks
...Show More Authors

In this paper we describe several different training algorithms for feed forward neural networks(FFNN). In all of these algorithms we use the gradient of the performance function, energy function, to determine how to adjust the weights such that the performance function is minimized, where the back propagation algorithm has been used to increase the speed of training. The above algorithms have a variety of different computation and thus different type of form of search direction and storage requirements, however non of the above algorithms has a global properties which suited to all problems.

View Publication Preview PDF
Publication Date
Sun Jan 01 2023
Journal Name
8th Engineering And 2nd International Conference For College Of Engineering – University Of Baghdad: Coec8-2021 Proceedings
Cascade position-torque control strategy based on function approximation technique (FAT) for flexible joint robots
...Show More Authors

View Publication
Crossref (1)
Crossref
Publication Date
Sun Dec 02 2012
Journal Name
Baghdad Science Journal
Stability of Back Propagation Training Algorithm for Neural Networks
...Show More Authors

In this paper, we derive and prove the stability bounds of the momentum coefficient µ and the learning rate ? of the back propagation updating rule in Artificial Neural Networks .The theoretical upper bound of learning rate ? is derived and its practical approximation is obtained

View Publication Preview PDF
Crossref
Publication Date
Mon Dec 01 2008
Journal Name
Journal Of Economics And Administrative Sciences
Neural Networks as a Discriminant Purposes
...Show More Authors

Discriminant between groups is one of the common procedures because of its ability to analyze many practical phenomena, and there are several methods can be used for this purpose, such as linear and quadratic discriminant functions. recently, neural networks is used as a tool to distinguish between groups.

In this paper the simulation is used to compare neural networks and classical method for classify observations to group that is belong to, in case of some variables that don’t follow the normal distribution. we use the proportion of number of misclassification observations to the all observations as a criterion of comparison.  

 

 

View Publication Preview PDF
Crossref
Publication Date
Fri Aug 12 2022
Journal Name
Future Internet
Improved DDoS Detection Utilizing Deep Neural Networks and Feedforward Neural Networks as Autoencoder
...Show More Authors

Software-defined networking (SDN) is an innovative network paradigm, offering substantial control of network operation through a network’s architecture. SDN is an ideal platform for implementing projects involving distributed applications, security solutions, and decentralized network administration in a multitenant data center environment due to its programmability. As its usage rapidly expands, network security threats are becoming more frequent, leading SDN security to be of significant concern. Machine-learning (ML) techniques for intrusion detection of DDoS attacks in SDN networks utilize standard datasets and fail to cover all classification aspects, resulting in under-coverage of attack diversity. This paper proposes a hybr

... Show More
View Publication Preview PDF
Scopus (31)
Crossref (24)
Scopus Clarivate Crossref
Publication Date
Tue Jun 03 2025
Journal Name
Periodicals Of Engineering And Natural Sciences (pen)
Comparison of some artificial neural networks for graduate students
...Show More Authors

Artificial Neural Networks (ANN) is one of the important statistical methods that are widely used in a range of applications in various fields, which simulates the work of the human brain in terms of receiving a signal, processing data in a human cell and sending to the next cell. It is a system consisting of a number of modules (layers) linked together (input, hidden, output). A comparison was made between three types of neural networks (Feed Forward Neural Network (FFNN), Back propagation network (BPL), Recurrent Neural Network (RNN). he study found that the lowest false prediction rate was for the recurrentt network architecture and using the Data on graduate students at the College of Administration and Economics, Univer

... Show More
View Publication
Crossref
Publication Date
Tue Aug 06 2013
Journal Name
Robotica
Function approximation technique-based adaptive virtual decomposition control for a serial-chain manipulator
...Show More Authors
SUMMARY<p>The virtual decomposition control (VDC) is an efficient tool suitable to deal with the full-dynamics-based control problem of complex robots. However, the regressor-based adaptive control used by VDC to control every subsystem and to estimate the unknown parameters demands specific knowledge about the system physics. Therefore, in this paper, we focus on reorganizing the equation of the VDC for a serial chain manipulator using the adaptive function approximation technique (FAT) without needing specific system physics. The dynamic matrices of the dynamic equation of every subsystem (e.g. link and joint) are approximated by orthogonal functions due to the minimum approximation errors produced. The contr</p> ... Show More
View Publication
Scopus (27)
Crossref (21)
Scopus Clarivate Crossref
Publication Date
Mon Dec 28 2020
Journal Name
International Journal Of Psychosocial Rehabilitation
Predicting the Sporting Achievement in the Pole Vault for Men Using Artificial Neural Networks
...Show More Authors

The physical sports sector in Iraq suffers from the problem of achieving sports achievements in individual and team games in various Asian and international competitions, for many reasons, including the lack of exploitation of modern, accurate and flexible technologies and means, especially in the field of information technology, especially the technology of artificial neural networks. The main goal of this study is to build an intelligent mathematical model to predict sport achievement in pole vaulting for men, the methodology of the research included the use of five variables as inputs to the neural network, which are Avarage of Speed (m/sec in Before distance 05 meters latest and Distance 05 meters latest, The maximum speed achieved in t

... Show More
View Publication Preview PDF