Method of selecting spatially distributed information for constructing training set of artificial neural networks

2019 ◽  
Author(s):  
Ashat Sydikhov ◽  
Alexander Buevich ◽  
Alexander Sergeev ◽  
Andrey Shichkin ◽  
Irina Subbotina ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Training Set ◽  
Distributed Information ◽  
Spatially Distributed ◽  
Artificial Neural

scholarly journals The Michigan 10-Degree Blue Spectral Survey as a Basis for Future Deep Schmidt Surveys

1995 ◽  
Vol 148 ◽  
pp. 292-295
Author(s):  
N. Houk ◽  
T. von Hippel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Automatic Classification ◽  
Training Set ◽  
Huge Number ◽  
Distance Methods ◽  
Artificial Neural ◽  
Metric Distance ◽  
Spectral Survey

AbstractThe Henry Draper stars are being systematically classified on the MK System, using the Curtis and Burrell Schmidt telescopes with photographic spectra having a dispersion of 108 Å/mm. Over 156,000 stars south of δ = +5°, have been classified leaving about 69,000 yet to do. The project is expected to be completed around the year 2004. This all-sky network of consistently classified spectra of very good quality should serve as a basis for future deep surveys. Such surveys will almost certainly be automated because of the huge number of stars to be dealt with. Von Hippel et al. at Cambridge plan to scan at least 150,000 of the spectra classified by Houk, using her plates to serve as a ‘training’ set for automatic classification using artificial neural networks. The same data can also be utilized for other methods of automatic classification including the metric-distance methods used by Kurtz and La Sala (Kurtz 1983). Even at lower dispersions, significantly more information can be obtained from Schmidt spectra than by doing Schmidt photometric colour surveys alone, though these are also valuable, especially when used in conjunction with spectra. We urge that large Schmidts not currently having prisms or other dispersive elements consider adding this equipment.

Unsupervised Learning in Artificial Neural Networks

2008 ◽  
pp. 48-90
Author(s):  
Darryl Charles ◽  
Colin Fyfe ◽  
Daniel Livingstone ◽  
Stephen McGlinchey
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Unsupervised Learning ◽  
Input Data ◽  
Descent Methods ◽  
Training Set ◽  
Human Capabilities ◽  
Artificial Neural ◽  
Do So

With the artificial neural networks which we have met so far, we must have a training set on which we already have the answers to the questions which we are going to pose to the network. Yet humans appear to be able to learn (indeed some would say can only learn) without explicit supervision. The aim of unsupervised learning is to mimic this aspect of human capabilities and hence this type of learning tends to use more biologically plausible methods than those using the error descent methods of the last two chapters. The network must self-organise and to do so, it must react to some aspect of the input data - typically either redundancy in the input data or clusters in the data; i.e. there must be some structure in the data to which it can respond.

Evaluating the Use of Artificial Neural Networks, Graph Theory, and Complexity Theory to Predict Automotive Assembly Defects

2016 ◽  
Author(s):  
Apurva Patel ◽  
Patrick Andrews ◽  
Joshua D. Summers
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prediction Models ◽  
Assembly Model ◽  
Training Set ◽  
Automotive Assembly ◽  
Artificial Neural ◽  
Training Set Selection ◽  
Selection Of ◽  
Assembly Models

Artificial Neural Networks (ANNs) have been used to predict assembly time and market value from assembly models. This was done by converting the assembly models into bipartite graphs and extracting 29 graph complexity metrics which were used to train the ANN prediction models. This paper presents the use of sub-assembly models instead of the entire assembly model to predict assembly quality defects at an automotive OEM. The size of the training set, order of the bipartite graph, selection of training set, and defect type were experimentally studied. With a training size of 28 parts, an interpolation focused training set selection, and second order graph seeding, over 70% of the predictions were within 100% of the target value. The study shows that with an increase in training size and careful selection of training sets, assembly defects can be predicted reliably from sub-assemblies complexity data.

Artificial neural networks in classification of NIR spectral data: Design of the training set

1996 ◽  
Vol 33 (1) ◽  
pp. 35-46 ◽  
Author(s):  
W. Wu ◽  
B. Walczak ◽  
D.L. Massart ◽  
S. Heuerding ◽  
F. Erni ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Spectral Data ◽  
Training Set ◽  
Artificial Neural ◽  
Data Design

scholarly journals Implementation of Incremental Learning in Artificial Neural Networks

10.29007/8559 ◽  
2018 ◽  
Author(s):  
Mariela Andrade ◽  
Eduardo Gasca ◽  
Eréndira Rendón
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Incremental Learning ◽  
Learning Algorithm ◽  
Human Memory ◽  
Support Vector ◽  
Training Set ◽  
New Knowledge ◽  
Target Network ◽  
Artificial Neural

Nowadays, the use of artificial neural networks (ANN), in particular the Multilayer Perceptron (MLP), is very popular for executing different tasks such as pattern recognition, data mining, and process automation. However, there are still weaknesses in these models when compared with human capabilities. A characteristic of human memory is the ability for learning new concepts without forgetting what we learned in the past, which has been a disadvantage in the field of artificial neural networks. How can we add new knowledge to the network without forgetting what has already been learned, without repeating the exhaustive ANN process? In an exhaustively training is used a complete training set, with all objects of all classes.In this work, we present a novel incremental learning algorithm for the MLP. New knowledge is incorporated into the target network without executing an exhaustive retraining. Objects of a new class integrate this knowledge, which was not included in the training of a source network. The algorithm consists in taking the final weights from the source network, doing a correction of these with the Support Vector Machine tools, and transferring the obtained weights to a target network. This last net is trained with a training set that it is previously preprocessed. The efficiency resulted of the target network is comparable with a net that is exhaustively trained.

Artificial neural networks for fly identification: A case study from the genera Tachina and Ectophasia (Diptera, Tachinidae)

Biologia ◽  
2007 ◽  
Vol 62 (4) ◽  
Author(s):  
Jaromír Vaňhara ◽  
Natália Muráriková ◽  
Igor Malenovský ◽  
Josef Havel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Correct Identification ◽  
Training Set ◽  
Image Analyser ◽  
Artificial Neural ◽  
Reliable Classification ◽  
The Right

AbstractThe classification methodology based on morphometric data and supervised artificial neural networks (ANN) was tested on five fly species of the parasitoid genera Tachina and Ectophasia (Diptera, Tachinidae). Objects were initially photographed, then digitalized; consequently the picture was scaled and measured by means of an image analyser. The 16 variables used for classification included length of different wing veins or their parts and width of antennal segments. The sex was found to have some influence on the data and was included in the study as another input variable. Better and reliable classification was obtained when data from both the right and left wings were entered, the data from one wing were however found to be sufficient. The prediction success (correct identification of unknown test samples) varied from 88 to 100% throughout the study depending especially on the number of specimens in the training set. Classification of the studied Diptera species using ANN is possible assuming a sufficiently high number (tens) of specimens of each species is available for the ANN training. The methodology proposed is quite general and can be applied for all biological objects where it is possible to define adequate diagnostic characters and create the appropriate database.

scholarly journals Influence of the Training Set Value on the Quality of the Neural Network to Identify Selected Moulding Sand Properties

2013 ◽  
Vol 13 (2) ◽  
pp. 49-52
Author(s):  
J. Jakubski ◽  
St. M. Dobosz ◽  
K. Major-Gabryś
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Assessment Method ◽  
Training Set ◽  
Data Set ◽  
The Neural Network ◽  
Artificial Neural ◽  
Moulding Sand ◽  
Small Change

Abstract Artificial neural networks are one of the modern methods of the production optimisation. An attempt to apply neural networks for controlling the quality of bentonite moulding sands is presented in this paper. This is the assessment method of sands suitability by means of detecting correlations between their individual parameters. This paper presents the next part of the study on usefulness of artificial neural networks to support rebonding of green moulding sand, using chosen properties of moulding sands, which can be determined fast. The effect of changes in the training set quantity on the quality of the network is presented in this article. It has been shown that a small change in the data set would change the quality of the network, and may also make it necessary to change the type of network in order to obtain good results.

Evaluating the Use of Artificial Neural Networks and Graph Complexity to Predict Automotive Assembly Quality Defects

2017 ◽  
Vol 17 (3) ◽  
Author(s):  
Apurva Patel ◽  
Patrick Andrews ◽  
Joshua D. Summers ◽  
Erin Harrison ◽  
Joerg Schulte ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prediction Models ◽  
Assembly Model ◽  
Training Set ◽  
Assembly Quality ◽  
Automotive Assembly ◽  
Artificial Neural ◽  
Training Set Selection ◽  
Selection Of

This paper presents the use of subassembly models instead of the entire assembly model to predict assembly quality defects at an automotive original equipment manufacturer (OEM). Specifically, artificial neural networks (ANNs) were used to predict assembly time and market value from assembly models. These models were converted into bipartite graphs from which 29 graph complexity metrics were extracted to train 18,900 ANN prediction models. The size of the training set, order of the bipartite graph, selection of training set, and defect type were experimentally studied. With a training size of 28 parts, an interpolation focused training set selection with a second-order graph seeding ensured that 70% of all predictions were within 100% of the target value. The study shows that with an increase in training size and careful selection of training sets, assembly defects can be predicted reliably from subassemblies' complexity data.

Sign in / Sign up

Export Citation Format

Share Document