scholarly journals ADAPTIVE SELECTION OF NEURAL NETWORKS FOR A COMMITTEE DECISION

2014 ◽  
pp. 23-30
Author(s):  
Arunas Lipnickas ◽  
Jozef Korbicz
Keyword(s):  
Neural Networks ◽  
Input Data ◽  
Majority Vote ◽  
Real Data ◽  
Data Sets ◽  
Committee Decision ◽  
Multiple Neural Networks ◽  
Median Rule ◽  
Data Point ◽  
Input Data Point

To improve recognition results, decisions of multiple neural networks can be aggregated into a committee decision. In contrast to the ordinary approach of utilising all neural networks available to make a committee decision, we propose creating adaptive committees, which are specific for each input data point. A prediction network is used to identify classification neural networks to be fused for making a committee decision about a given input data point. The jth output value of the prediction network expresses the expectation level that the jth classification neural network will make a correct decision about the class label of a given input data point. The proposed technique is tested in three aggregation schemes, namely majority vote, averaging, and aggregation by the median rule and compared with the ordinary neural networks fusion approach. The effectiveness of the approach is demonstrated on three well known real data sets and also applied to fault identification of the actuator valve at one sugar factory within the DAMADICS RTN.

SELECTING NEURAL NETWORKS FOR A COMMITTEE DECISION

2002 ◽  
Vol 12 (05) ◽  
pp. 351-361 ◽  
Author(s):  
ANTANAS VERIKAS ◽  
ARUNAS LIPNICKAS ◽  
KERSTIN MALMQVIST
Keyword(s):  
Neural Networks ◽  
Input Data ◽  
Majority Vote ◽  
Real Data ◽  
Data Sets ◽  
Committee Decision ◽  
Multiple Neural Networks ◽  
Median Rule ◽  
Data Point ◽  
Input Data Point

To improve recognition results, decisions of multiple neural networks can be aggregated into a committee decision. In contrast to the ordinary approach of utilizing all neural networks available to make a committee decision, we propose creating adaptive committees, which are specific for each input data point. A prediction network is used to identify classification neural networks to be fused for making a committee decision about a given input data point. The jth output value of the prediction network expresses the expectation level that the jth classification neural network will make a correct decision about the class label of a given input data point. The proposed technique is tested in three aggregation schemes, namely majority vote, averaging, and aggregation by the median rule and compared with the ordinary neural networks fusion approach. The effectiveness of the approach is demonstrated on two artificial and three real data sets.

Reduced Representation by Neural Networks with Restricted Receptive Fields

1995 ◽  
Vol 7 (3) ◽  
pp. 507-517 ◽  
Author(s):  
Marco Idiart ◽  
Barry Berk ◽  
L. F. Abbott
Keyword(s):  
Neural Networks ◽  
Biological Networks ◽  
Input Data ◽  
Hebbian Learning ◽  
Receptive Fields ◽  
Principal Component ◽  
Data Sets ◽  
Reduced Representation ◽  
Learning Rules ◽  
Reduced Representations

Model neural networks can perform dimensional reductions of input data sets using correlation-based learning rules to adjust their weights. Simple Hebbian learning rules lead to an optimal reduction at the single unit level but result in highly redundant network representations. More complex rules designed to reduce or remove this redundancy can develop optimal principal component representations, but they are not very compelling from a biological perspective. Neurons in biological networks have restricted receptive fields limiting their access to the input data space. We find that, within this restricted receptive field architecture, simple correlation-based learning rules can produce surprisingly efficient reduced representations. When noise is present, the size of the receptive fields can be optimally tuned to maximize the accuracy of reconstructions of input data from a reduced representation.

Apply Artificial Neural Networks to Estimate Stress Distribution around Holes Edge in Composites

2012 ◽  
Vol 490-495 ◽  
pp. 3105-3108
Author(s):  
Kamran Pazand ◽  
Younes Alizadeh
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Stress Distribution ◽  
Composite Laminates ◽  
Composite Plate ◽  
Input Data ◽  
Data Sets ◽  
Fast Determination ◽  
Artificial Neural

The purpose of this paper is to estimate the fast determination of stress distribution around a circular hole in symmetric composite laminates under in-plane loading. For this purpose calculation of stress values in the composite plate around edge holes in different plies position for a finite number of input data sets using the Lekhnitskii expressions and code program. The resulting data would then be used to train artificial neural networks (ANN) which would be able to predict –accurately enough- those quantities throughout the composite plate body for any given input value in any position ply and fore and stress that impose.

A Center Initialization Method Based on Merger of Divisions of a Data Set along Each Dimension

2013 ◽  
Vol 333-335 ◽  
pp. 1269-1272
Author(s):  
Guang Hui Chen
Keyword(s):  
Real Data ◽  
Cluster Center ◽  
Data Sets ◽  
Data Set ◽  
Initial Cluster ◽  
Data Point

this paper proposes a hierarchical division method that divides a data set into two subsets along each dimension, and merges them into a division of the data set. Then the initial cluster centers are located in dense and separate subsets of the data set, and the means of data point in these subsets are selected as the initial cluster centers. Thus a new cluster center initialization method is developed. Experiments on real data sets show that the proposed cluster center initialization method is desirable.

Data mining in manufacturing: Significance analysis of process parameters

2008 ◽  
Vol 222 (11) ◽  
pp. 1503-1516 ◽  
Author(s):  
M Perzyk ◽  
R Biernacki ◽  
J Kozlowski
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Process Parameters ◽  
Regression Models ◽  
Simulated Data ◽  
Real Data ◽  
Support Vector ◽  
Data Sets ◽  
Interaction Factors

Determination of the most significant manufacturing process parameters using collected past data can be very helpful in solving important industrial problems, such as the detection of root causes of deteriorating product quality, the selection of the most efficient parameters to control the process, and the prediction of breakdowns of machines, equipment, etc. A methodology of determination of relative significances of process variables and possible interactions between them, based on interrogations of generalized regression models, is proposed and tested. The performance of several types of data mining tool, such as artificial neural networks, support vector machines, regression trees, classification trees, and a naïve Bayesian classifier, is compared. Also, some simple non-parametric statistical methods, based on an analysis of variance (ANOVA) and contingency tables, are evaluated for comparison purposes. The tests were performed using simulated data sets, with assumed hidden relationships, as well as on real data collected in the foundry industry. It was found that the performance of significance and interaction factors obtained from regression models, and, in particular, neural networks, is satisfactory, while the other methods appeared to be less accurate and/or less reliable.

scholarly journals An introduction to distributed training of deep neural networks for segmentation tasks with large seismic data sets

Geophysics ◽  
2021 ◽  
Vol 86 (6) ◽  
pp. KS151-KS160
Author(s):  
Claire Birnie ◽  
Haithem Jarraya ◽  
Fredrik Hansteen
Keyword(s):  
Neural Networks ◽  
Input Data ◽  
Model Performance ◽  
Microseismic Monitoring ◽  
Training Data ◽  
Data Sets ◽  
Distributed Training ◽  
Spatiotemporal Information ◽  
Training Approach ◽  
Data Generator

Deep learning applications are drastically progressing in seismic processing and interpretation tasks. However, most approaches subsample data volumes and restrict model sizes to minimize computational requirements. Subsampling the data risks losing vital spatiotemporal information which could aid training, whereas restricting model sizes can impact model performance, or in some extreme cases renders more complicated tasks such as segmentation impossible. We have determined how to tackle the two main issues of training of large neural networks (NNs): memory limitations and impracticably large training times. Typically, training data are preloaded into memory prior to training, a particular challenge for seismic applications in which the data format is typically four times larger than that used for standard image processing tasks (float32 versus uint8). Based on an example from microseismic monitoring, we evaluate how more than 750 GB of data can be used to train a model by using a data generator approach, which only stores in memory the data required for that training batch. Furthermore, efficient training over large models is illustrated through the training of a seven-layer U-Net with input data dimensions of [Formula: see text] (approximately [Formula: see text] million parameters). Through a batch-splitting distributed training approach, the training times are reduced by a factor of four. The combination of data generators and distributed training removes any necessity of data subsampling or restriction of NN sizes, offering the opportunity to use larger networks, higher resolution input data, or move from 2D to 3D problem spaces.

scholarly journals Weighted Bagging in Decision Trees: Data Mining

2020 ◽  
Vol 1 (1) ◽  
pp. 1-14
Author(s):  
Yousef Elgimati
Keyword(s):  
Decision Trees ◽  
Learning Algorithm ◽  
Majority Vote ◽  
Random Noise ◽  
Real Data ◽  
Data Sets ◽  
Bootstrap Sample ◽  
Training Set ◽  
Multiple Classifier ◽  
Better Than

The main focus of this paper is on the use of resampling techniques to construct predictive models from data and the goal is to identify the best possible model which can produce better predications. Bagging or Bootstrap aggregating is a general method for improving the performance of given learning algorithm by using a majority vote to combine multiple classifier outputs derived from a single classifier on a bootstrap resample version of a training set. A bootstrap sample is generated by a random sample with replacement from the original training set. Inspired by the idea of bagging, we present an improved method based on a distance function in decision trees, called modified bagging (or weighted Bagging) in this study. The experimental results show that modified bagging is superior to the usual majority vote. These results are confirmed by both real data and artificial data sets with random noise. The Modified bagged classifier performs significantly better than usual bagging on various tree levels for all sample sizes. An interesting observation is that the weighted bagging performs somewhat better than usual bagging with sumps.

scholarly journals USING A MIXTURE OF EXPERTS’ APPROACH TO SOLVE THE FORECASTING TASK

Aviation ◽  
2014 ◽  
Vol 18 (3) ◽  
pp. 129-133
Author(s):  
Victor Sineglazov ◽  
Elena Chumachenko ◽  
Vladyslav Gorbatyuk
Keyword(s):  
Neural Networks ◽  
Demand Forecasting ◽  
Real Data ◽  
Air Transport ◽  
Aviation Industry ◽  
Mixture Of Experts ◽  
New Approach ◽  
Multiple Neural Networks

The forecasting problem appears frequently in the aviation industry (demand forecasting, air transport movement forecasting, etc.). In this article, a new approach based on multiple neural networks of different topologies is introduced. An algorithm was tested on real data and showed better results compared to several other methods. This shows its suitability for further usage in aviation forecasting tasks.

ENSEMBLE COMPETITIVE LEARNING NEURAL NETWORKS WITH REDUCED INPUT DIMENSION

1995 ◽  
Vol 06 (02) ◽  
pp. 133-142 ◽  
Author(s):  
JONGWAN KIM ◽  
JESUNG AHN ◽  
SEONGWON CHO
Keyword(s):  
Neural Networks ◽  
Competitive Learning ◽  
One Dimension ◽  
Final Decision ◽  
Data Sets ◽  
Multiple Neural Networks ◽  
Ensemble Neural Networks ◽  
Output Neurons ◽  
Improved Performance ◽  
Classification Information

Conventional neural networks utilize all the dimensions of the original input patterns for training and classification. However, a particular attribute of the input patterns does not necessarily contribute to classification and may even cause misclassification in certain cases. A new ensemble competitive learning method using the reduced input dimension is proposed. In contrast to the previous ensemble neural networks which adjust learning parameters, the proposed method takes advantage of the information in each dimension of the input patterns. Since the degree of contribution of each attribute to classification is not known beforehand, the different input data sets with one dimension reduced are presented to multiple neural networks. The classification information from each competitive learning neural network is then combined to make a final decision for classification. In order to improve classification accuracy, the ambiguous output neurons are eliminated which cannot be assigned to any class after training. We use three consensus schemes to judge the classification using ensemble neural networks. The experimental results with remote sensing and speech data indicate the improved performance of the proposed method.

scholarly journals Architecture Selection in Neural Networks by Statistical and Machine Learning

2019 ◽  
Vol 12 (Issue 3) ◽  
pp. 76-89
Author(s):  
Cagdas Hakan Aladag
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Regression Analysis ◽  
Artificial Neural Networks ◽  
Real Data ◽  
Statistical Hypothesis ◽  
Data Sets ◽  
Artificial Neural ◽  
Trial And Error Method ◽  
Error Method

One of the biggest problems in using artificial neural networks is to determine the best architecture. This is a crucial problem since there are no general rules to select the best architecture structure. Selection of the best architecture is to determine how many neurons should be used in the layers of a network. It is a well-known fact that using a proper architecture structure directly affect the performance of the method. Therefore, various approaches ranging from trial and error method to heuristic optimization algorithms have been suggested to solve this problem in the literature. Although there have been systematical approaches in the literature, trial and error method has been widely used in various applications to find a good architecture. This study propose a new architecture selection method based on statistical and machine learning. The proposed method utilizes regression analysis that is a supervised learning technique in machine learning. In this new architecture selection approach, it is aimed to combine statistical and machine learning to reach good architectures which has high performance. The proposed approach brings a new perspective since it is possible to perform statistical hypothesis tests and to statistically evaluate the obtained results when artificial neural networks are used. The best architecture structure can be statistically determined in the proposed approach. In addition to this, the proposed approach provides some important advantages. This is the first study using a statistical method to utilize statistical hypothesis tests in artificial neural networks. Using regression analysis is easy to use so applying the proposed method is also easy. And, the proposed approach saves time since the best architecture is determined by regression analysis. Furthermore, it is possible to make inference for architectures which is not examined. The proposed approach is applied to three real data sets to show the applicability of the approach. The obtained results show that the proposed method gives very satisfactory results for real data sets.

Sign in / Sign up

Export Citation Format

Share Document