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.

scholarly journals Optimal Artificial Neural Network Type Selection Method for Usage in Smart House Systems

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 47
Author(s):  
Vasyl Teslyuk ◽  
Artem Kazarian ◽  
Natalia Kryvinska ◽  
Ivan Tsmots
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Input Data ◽  
Optimization Criterion ◽  
Fuzzy Input ◽  
Different Types ◽  
Smart House ◽  
Artificial Neural

In the process of the “smart” house systems work, there is a need to process fuzzy input data. The models based on the artificial neural networks are used to process fuzzy input data from the sensors. However, each artificial neural network has a certain advantage and, with a different accuracy, allows one to process different types of data and generate control signals. To solve this problem, a method of choosing the optimal type of artificial neural network has been proposed. It is based on solving an optimization problem, where the optimization criterion is an error of a certain type of artificial neural network determined to control the corresponding subsystem of a “smart” house. In the process of learning different types of artificial neural networks, the same historical input data are used. The research presents the dependencies between the types of neural networks, the number of inner layers of the artificial neural network, the number of neurons on each inner layer, the error of the settings parameters calculation of the relative expected results.

scholarly journals Saturated Hydraulic Conductivity Estimation Using Artificial Neural Networks

Water ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 705
Author(s):  
Josué Trejo-Alonso ◽  
Carlos Fuentes ◽  
Carlos Chávez ◽  
Antonio Quevedo ◽  
Alfonso Gutierrez-Lopez ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Hydraulic Conductivity ◽  
Input Data ◽  
Logistic Function ◽  
Saturated Hydraulic Conductivity ◽  
Irrigation District ◽  
Pedotransfer Functions ◽  
Back Propagation Algorithm ◽  
Artificial Neural

In the present work, we construct several artificial neural networks (varying the input data) to calculate the saturated hydraulic conductivity (KS) using a database with 900 measured samples obtained from the Irrigation District 023, in San Juan del Rio, Queretaro, Mexico. All of them were constructed using two hidden layers, a back-propagation algorithm for the learning process, and a logistic function as a nonlinear transfer function. In order to explore different arrays for neurons into hidden layers, we performed the bootstrap technique for each neural network and selected the one with the least Root Mean Square Error (RMSE) value. We also compared these results with pedotransfer functions and another neural networks from the literature. The results show that our artificial neural networks obtained from 0.0459 to 0.0413 in the RMSE measurement, and 0.9725 to 0.9780 for R2, which are in good agreement with other works. We also found that reducing the amount of the input data offered us better results.

Rainfall Prediction by Artificial Neural Networks Trained using Different Climate Variables

2021 ◽  
Author(s):  
Mateus Alexandre da Silva ◽  
Marina Neves Merlo ◽  
Michael Silveira Thebaldi ◽  
Danton Diego Ferreira ◽  
Felipe Schwerz ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Input Data ◽  
Back Propagation ◽  
Metropolitan Region ◽  
Climate Variables ◽  
Back Propagation Algorithm ◽  
Rainfall Prediction ◽  
Artificial Neural ◽  
Belo Horizonte

Abstract Predicting rainfall can prevent and mitigate damages caused by its deficit or excess, besides providing necessary tools for adequate planning for the use of water. This research aimed to predict the monthly rainfall, one month in advance, in four municipalities in the metropolitan region of Belo Horizonte, using artificial neural networks (ANN) trained with different climate variables, and to indicate the suitability of such variables as inputs to these models. The models were developed through the MATLAB® software version R2011a, using the NNTOOL toolbox. The ANN’s were trained by the multilayer perceptron architecture and the Feedforward and Back propagation algorithm, using two combinations of input data were used, with 2 and 6 variables, and one combination of input data with 3 of the 6 variables most correlated to observed rainfall from 1970 to 1999, to predict the rainfall from 2000 to 2009. The most correlated variables to the rainfall of the following month are the sequential number corresponding to the month, total rainfall and average compensated temperature, and the best performance was obtained with these variables. Furthermore, it was concluded that the performance of the models was satisfactory; however, they presented limitations for predicting months with high rainfall.

Real-Time Recoloring Ishihara Plates Using Artificial Neural Networks for Helping Colorblind People

2020 ◽  
pp. 138-156
Author(s):  
Martín Montes Rivera ◽  
Alejandro Padilla ◽  
Juana Canul-Reich ◽  
Julio Ponce
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Real Time ◽  
Input Data ◽  
Traffic Signals ◽  
Educational Materials ◽  
Ishihara Test ◽  
Artificial Neural ◽  
Intelligence Technique

Vision sense is achieved using cells called rods (luminosity) and cones (color). Color perception is required when interacting with educational materials, industrial environments, traffic signals, among others, but colorblind people have difficulties perceiving colors. There are different tests for colorblindness like Ishihara plates test, which have numbers with colors that are confused with colorblindness. Advances in computer sciences produced digital assistants for colorblindness, but there are possibilities to improve them using artificial intelligence because its techniques have exhibited great results when classifying parameters. This chapter proposes the use of artificial neural networks, an artificial intelligence technique, for learning the colors that colorblind people cannot distinguish well by using as input data the Ishihara plates and recoloring the image by increasing its brightness. Results are tested with a real colorblind people who successfully pass the Ishihara test.

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.

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

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.

Artificial Neural Networks for Prediction

2011 ◽  
pp. 54-58
Author(s):  
Rafael Marti
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Intelligent Systems ◽  
Intelligent System ◽  
Human Capabilities ◽  
Design And Implementation ◽  
Starting Point ◽  
Input Signals ◽  
Artificial Neural ◽  
The Brain

The design and implementation of intelligent systems with human capabilities is the starting point to design Artificial Neural Networks (ANNs). The original idea takes after neuroscience theory on how neurons in the human brain cooperate to learn from a set of input signals to produce an answer. Because the power of the brain comes from the number of neurons and the multiple connections between them, the basic idea is that connecting a large number of simple elements in a specific way can form an intelligent system.

scholarly journals Predicting Tooth Surface Loss Using Genetic Algorithms-Optimized Artificial Neural Networks

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Ali Al Haidan ◽  
Osama Abu-Hammad ◽  
Najla Dar-Odeh
Keyword(s):  
Neural Networks ◽  
Mathematical Model ◽  
Genetic Algorithms ◽  
Artificial Neural Networks ◽  
Input Data ◽  
Tooth Surface ◽  
Output Data ◽  
Surface Loss ◽  
Artificial Neural ◽  
High Degree

Our aim was to predict tooth surface loss in individuals without the need to conduct clinical examinations. Artificial neural networks (ANNs) were used to construct a mathematical model. Input data consisted of age, smoker status, type of tooth brush, brushing, and consumption of pickled food, fizzy drinks, orange, apple, lemon, and dried seeds. Output data were the sum of tooth surface loss scores for selected teeth. The optimized constructed ANN consisted of 2-layer network with 15 neurons in the first layer and one neuron in the second layer. The data of 46 subjects were used to build the model, while the data of 15 subjects were used to test the model. Accepting an error of ±5 scores for all chosen teeth, the accuracy of the network becomes more than 80%. In conclusion, this study shows that modeling tooth surface loss using ANNs is possible and can be achieved with a high degree of accuracy.

Sign in / Sign up

Export Citation Format

Share Document