Feedforward Neural Network Models for Spatial Data Classification and Rule Learning

Error backpropagation in feedforward neural network models is a popular learning algorithm that has its roots in nonlinear estimation and optimization. It is being used routinely to calculate error gradients in nonlinear systems with hundreds of thousands of parameters. However, the classical architecture for backpropagation has severe restrictions. The extension of backpropagation to networks with recurrent connections will be reviewed. It is now possible to efficiently compute the error gradients for networks that have temporal dynamics, which opens applications to a host of problems in systems identification and control.

Download Full-text

Assessing State of the Art on Artificial Neural Network Paradigms for Level of Eutrophication Estimation of Water Bodies

IAES International Journal of Artificial Intelligence (IJ-AI) ◽

10.11591/ijai.v5.i4.pp135-142 ◽

2016 ◽

Vol 5 (4) ◽

pp. 135

Author(s):

Tushar Anthwal ◽

M K Pandey

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Spatial Data ◽

Network Models ◽

Water Bodies ◽

Statistical Interpretation ◽

Estimation Of Parameters ◽

Neural Network Models ◽

Resultant Data ◽

Artificial Neural

With growing power of computer and blend of intelligent soft wares, the interpretation and analytical capabilities of the system had shown an excellent growth, providing intelligence solutions to almost every computing problem. In this direction here we are trying to identify how different geocomputation techniques had been implemented for estimation of parameters on water bodies so as to identify the level of contamination leading to the different level of eutrophication. The main mission of this paper is to identify state-of-art in artificial neural network paradigms that are prevailing and effective in modeling and combining spatial data for anticipation. Among this, our interest is to identify different analysis techniques and their parameters that are mainly used for quality inspection of lakes and estimation of nutrient pollutant content in it, and different neural network models that offered the forecasting of level of eutrophication in the water bodies. Different techniques are analyzed over the main steps;-assimilation of spatial data, statistical interpretation technique, observed parameters used for eutrophication estimation and accuracy of resultant data.

Download Full-text

Data Classification with an Improved Weightless Neural Network

Journal of IT in Asia ◽

10.33736/jita.401.2005 ◽

2017 ◽

Vol 1 (1) ◽

pp. 17-34

Author(s):

W.K. Lai ◽

G. Coghill

Keyword(s):

Neural Network ◽

Multilayer Perceptron ◽

Hardware Implementation ◽

Network Models ◽

Data Classification ◽

Data Sets ◽

Neural Network Models ◽

Multilayer Perceptron Network ◽

Pass Through

This paper examines the performance of an enhanced weightless neural network as a classifier. Like all earlier weightless neural network models, this network learns in one pass through the data This new weightless neural network has shown significant gains in the classifiction accuracy over the earlier Deterministic RAN Network (DARN), on a variety of problems. In addition, some comparisons between the DARN and the proposed network are presented. This will also include some evidence on how a standard Multilayer Perceptron network would behave on the same data sets. Finally, hardware implementation issues are discussed.

Download Full-text

FEEDFORWARD NEURAL NETWORK MODELS FOR HANDLING CLASS OVERLAP AND CLASS IMBALANCE

International Journal of Neural Systems ◽

10.1142/s012906570500030x ◽

2005 ◽

Vol 15 (05) ◽

pp. 323-338 ◽

Cited By ~ 3

Author(s):

RALF KRETZSCHMAR ◽

NICOLAOS B. KARAYIANNIS ◽

FRITZ EGGIMANN

Keyword(s):

Neural Network ◽

Neural Networks ◽

Error Function ◽

Class Imbalance ◽

Network Models ◽

Feedforward Neural Networks ◽

Feedforward Neural Network ◽

Neural Network Models ◽

Real World Data ◽

Special Case

This paper proposes a framework for training feedforward neural network models capable of handling class overlap and imbalance by minimizing an error function that compensates for such imperfections of the training set. A special case of the proposed error function can be used for training variance-controlled neural networks (VCNNs), which are developed to handle class overlap by minimizing an error function involving the class-specific variance (CSV) computed at their outputs. Another special case of the proposed error function can be used for training class-balancing neural networks (CBNNs), which are developed to handle class imbalance by relying on class-specific correction (CSC). VCNNs and CBNNs are compared with conventional feedforward neural networks (FFNNs), quantum neural networks (QNNs), and resampling techniques. The properties of VCNNs and CBNNs are illustrated by experiments on artificial data. Various experiments involving real-world data reveal the advantages offered by VCNNs and CBNNs in the presence of class overlap and class imbalance.

Download Full-text