Results of Bias-variance Tests on Multi-layer Perceptron Neural Networks

2001 ◽  
Vol 5 (5) ◽  
pp. 300-305
Author(s):  
Wimpie D. Nortje ◽  
◽  
Johann E. W. Holm ◽  
Gerhard P. Hancke ◽  
Imre. J. Rudas ◽  
...  
Keyword(s):  
Neural Networks ◽  
Bayesian Networks ◽  
Training Data ◽  
Computational Time ◽  
Bayesian Techniques ◽  
Multiple Networks ◽  
The Neural Networks ◽  
Computational Errors ◽  
Bias Variance ◽  
Selection Of

Training neural networks involves selection of a set of network parameters, or weights, on account of fitting a non-linear model to data. Due to the bias in the training data and small computational errors, the neural networks’ opinions are biased. Some improvement is possible when multiple networks are used to do the classification. This approach is similar to taking the average of a number of biased opinions in order to remove some of the bias that resulted from training. Bayesian networks are effective in removing some of the bias associated with training, but Bayesian techniques are tedious in terms of computational time. It is for this reason that alternatives to Bayesian networks are investigated.

scholarly journals Localization of Scattering Objects Using Neural Networks

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 11
Author(s):  
Domonkos Haffner ◽  
Ferenc Izsák
Keyword(s):  
Neural Networks ◽  
Plane Waves ◽  
Measurement Data ◽  
Scattered Wave ◽  
Training Data ◽  
Data Set ◽  
Main Compound ◽  
Incident Plane ◽  
The Neural Networks ◽  
Simulation Package

The localization of multiple scattering objects is performed while using scattered waves. An up-to-date approach: neural networks are used to estimate the corresponding locations. In the scattering phenomenon under investigation, we assume known incident plane waves, fully reflecting balls with known diameters and measurement data of the scattered wave on one fixed segment. The training data are constructed while using the simulation package μ-diff in Matlab. The structure of the neural networks, which are widely used for similar purposes, is further developed. A complex locally connected layer is the main compound of the proposed setup. With this and an appropriate preprocessing of the training data set, the number of parameters can be kept at a relatively low level. As a result, using a relatively large training data set, the unknown locations of the objects can be estimated effectively.

scholarly journals Data Size Requirement for Forecasting Daily Crude Oil Price with Neural Networks

2019 ◽  
Vol 66 (3) ◽  
pp. 363-388
Author(s):  
Serkan Aras ◽  
Manel Hamdi
Keyword(s):  
Neural Networks ◽  
Crude Oil ◽  
Significant Interaction ◽  
Statistical Tests ◽  
Oil Price ◽  
Training Data ◽  
Forecasting Model ◽  
Crude Oil Price ◽  
Crude Oil Prices ◽  
Selection Of

When the literature regarding applications of neural networks is investigated, it appears that a substantial issue is what size the training data should be when modelling a time series through neural networks. The aim of this paper is to determine the size of training data to be used to construct a forecasting model via a multiple-breakpoint test and compare its performance with two general methods, namely, using all available data and using just two years of data. Furthermore, the importance of the selection of the final neural network model is investigated in detail. The results obtained from daily crude oil prices indicate that the data from the last structural change lead to simpler architectures of neural networks and have an advantage in reaching more accurate forecasts in terms of MAE value. In addition, the statistical tests show that there is a statistically significant interaction between data size and stopping rule.

Applying Fuzzy Logic and Neural Network to Rheumatism Treatment in Oriental Medicine

2007 ◽  
Vol 11 (1) ◽  
pp. 4-10 ◽  
Author(s):  
Cao Thang ◽  
◽  
Eric W. Cooper ◽  
Yukinobu Hoshino ◽  
Katsuari Kamei ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fuzzy Logic ◽  
Decision Support ◽  
Decision Support System ◽  
Support System ◽  
Fuzzy Inference ◽  
Training Data ◽  
Oriental Medicine ◽  
The Neural Networks

In this paper, we present an application of soft computing into a decision support system RETS: Rheumatic Evaluation and Treatment System in Oriental Medicine (OM). Inputs of the system are severities of observed symptoms on patients and outputs are a diagnosis of rheumatic states, its explanations and herbal prescriptions. First, an outline of the proposed decision support system is described after considering rheumatic diagnoses and prescriptions by OM doctors. Next, diagnosis by fuzzy inference and prescription by neural networks are described. By fuzzy inference, RETS diagnoses the most appropriate rheumatic state in which the patient appears to be infected, then it gives a prescription written in suitable herbs with reasonable amounts based on neural networks. Training data for the neural networks is collected from experienced OM physicians and OM text books. Finally, we describe evaluations and restrictions of RETS.

Information Based Selection of Neural Networks Training Data for S.I. Engine Mapping

2001 ◽  
Author(s):  
Ivan Arsie ◽  
Fabrizio Marotta ◽  
Cesare Pianese ◽  
Gianfranco Rizzo
Keyword(s):  
Neural Networks ◽  
Training Data ◽  
Selection Of

Counting the Hidden Defects in Software Documents

2010 ◽  
pp. 519-538
Author(s):  
Frank Padberg
Keyword(s):  
Neural Networks ◽  
Training Data ◽  
Estimation Methods ◽  
Model Parameters ◽  
Small Data ◽  
Data Sets ◽  
Software Inspection ◽  
Bayesian Techniques ◽  
Standard Quality ◽  
Small Data Sets

The author uses neural networks to estimate how many defects are hidden in a software document. Input for the models are metrics that get collected when effecting a standard quality assurance technique on the document, a software inspection. For inspections, the empirical data sets typically are small. The author identifies two key ingredients for a successful application of neural networks to small data sets: Adapting the size, complexity, and input dimension of the networks to the amount of information available for training; and using Bayesian techniques instead of cross-validation for determining model parameters and selecting the final model. For inspections, the machine learning approach is highly successful and outperforms the previously existing defect estimation methods in software engineering by a factor of 4 in accuracy on the standard benchmark. The author’s approach is well applicable in other contexts that are subject to small training data sets.

scholarly journals High-Lift Optimization Design Using Neural Networks on a Multi-Element Airfoil

1998 ◽  
Author(s):  
Roxana M. Greenman ◽  
Karlin R. Roth
Keyword(s):  
Neural Networks ◽  
Optimization Design ◽  
Initial Conditions ◽  
Angle Of Attack ◽  
Computational Time ◽  
Data Set ◽  
High Lift ◽  
Marquardt Algorithm ◽  
Gradient Based ◽  
The Neural Networks

Abstract The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle of attack at which it occurs. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag, and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural networks were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 83% compared with traditional gradient-based optimization procedures for multiple optimization runs.

scholarly journals Modeling of Duck Density and Complex Stocking Time in Rice-Duck Agroecosystems in Terms of Economic and Ecological Benefits

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Dahong Xiong ◽  
Kui Fang ◽  
Ying Luo ◽  
Xiaopeng Dai
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Quantitative Assessment ◽  
Intelligent Algorithm ◽  
Ecological Benefits ◽  
Hybrid Intelligent Algorithm ◽  
Numerical Examples ◽  
The Neural Networks ◽  
Fitting Ability ◽  
Selection Of

Rice-duck integrated farming is an effective step under today’s sustainable development background. To make better economic and ecological benefits, a rice-duck agroecosystem is established and kept, in which the paddy field, rice, and the duck mutually promote one another. But the duck density and complex stocking time must be rationally selected. Aiming to attain quantitative assessment and optimal selection of the duck density and complex stocking time in this kind of systems, a methodology based on proposed mathematical models in terms of comparative economic and ecological benefits is addressed. Then the models are solved by a hybrid intelligent algorithmNN-GAthat integrates the Neural Networks (NN) and Genetic Algorithm (GA), making use of the fitting ability in nonlinear fitness context of Neural Networks and the optimization ability of the Genetic Algorithm. Besides, numerical examples are demonstrated in order to test the proposed models. Results reveal that the methodology is reasonable and feasible.

Sign in / Sign up

Export Citation Format

Share Document