MAGNETIC ELEMENTS OF NEURAL NETWORKS. PROPERTIES OF MAGNETIC INHOMOGENEITIES IN RESTRICTED GEOMETRIES

2021 ◽  
Vol 0 (1) ◽  
pp. 81-86
Author(s):  
A.R. MINIBAEVA ◽  
◽  
Z.V. GAREEVA ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Magnetic Anisotropy ◽  
Domain Structure ◽  
Magnetic State ◽  
Magnetic Nanostructures ◽  
External Factors ◽  
Magnetic Elements ◽  
Magnetic States ◽  
Moriya Interaction

This paper discusses the prospects for using magnetic nanostructures as elements of neural networks. At present neural network learning programs are actively used in analyzing and processing large data arrays; however, the development of computer technologies based on the neural network principle still remains open. Possibilities for using magnetic elements as physical carriers of information bits in these systems attract much attention from researchers and technologists due to the presence of several easily controlled parameters (order parameter) in the magnetic system, possibilities for the dimensionality reduction in magnetic elements by using magnetic nanostructures (domain boundaries, vortices, ckyrmions), superquick switching between magnetic states and some other factors. One of the key aspects of research in this regard is to determine basic controlled magnetic parameters in restricted geometries and to identify ways of controlling these parameters through internal and external factors. The paper presents a research on the magnetic ground state in restricted geometries. It deals with the magnetic state rebuilding in the system under changes in both external factors (applied magnetic field, sample dimensions) and internal ones (magnetic anisotropy constant, Dzyaloshinskii-Moriya interaction constant). Calculations were performed within the framework of micromagnetic modelling using the Object Oriented MicroMagnetic Framework ( OOMMF) sogtware. It is shown that the anisotropic exchange interaction (Dzyaloshinskii-Moriya interaction) has a significant effect on the magnetization distribution in restricted geometries. Namely, when changing the value of the Dzyaloshinskii-Moriya constant in the system with uniaxial magnetic anisotropy there is a series of phase transitions observed between magnetic states of different types: transitions from the homogenous magnetic state into the skyrmion-type vortex state (domain structure with the skyrmion-type unidomain state) with subsequent domain structure reversal when changing the value of the Dzyaloshinskii-Moriya constant. In the case of magnetic anisotropy of easy -axis type, chirality and properties of the structures in question do not depend on the constant symbol of the Dzyaloshinskii-Moriya interaction.

The effect of Dzyaloshinskii–Moriya interaction on direct and backward transition between magnetic states of Pt/Co/Ir/Co/Pr synthetic ferrimagnet

2021 ◽  
Vol 6 (3) ◽  
pp. 167-178
Author(s):  
Artem D. Talantsev ◽  
Ekaterina I. Kunitsyna ◽  
Roman B. Morgunov
Keyword(s):  
Thin Layer ◽  
Domain Structure ◽  
Magnetization Reversal ◽  
Domain Walls ◽  
Ferromagnetic Layers ◽  
Magneto Optical Kerr Effect ◽  
Magnetic States ◽  
Fluctuation Fields ◽  
Moriya Interaction ◽  
Effect Technique

In this paper, we present the study of domain structure accompanying interstate transitions in Pt/Co/Ir/Co/Pr synthetic ferrimagnet (SF) of 1.1 nm thick and 0.6 – 1.0 nm thin ferromagnetic Co layers. Variation in the thickness of the thin layer causes noticeable changes in the domain structure and mechanism of magnetization reversal revealed by MOKE (Magneto-Optical Kerr Effect) technique. Magnetization reversal includes coherent rotation of magnetization of the ferromagnetic layers, generation of magnetic nuclei, spreading of domain walls (DW), and development of areas similar with strip domains, dependently on thickness of the thin layer. Inequivalence of the direct and backward transitions between magnetic states of SF with parallel and antiparallel magnetizations was observed in sample with thin layer thicknesses 0.8 nm and 1.0 nm. Asymmetry of the transition between these states is expressed in difference fluctuation fields and shapes of reversal magnetization nucleus contributing to the correspondent forward and backward transitions. We proposed simple model based on asymmetry of Dzyaloshinskii–Moriya interaction. This model explains competition between nucleation and domain wall propagation due to increase/decrease of the DW energy dependently on direction of the spin rotation into the DW in respect to external field.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Magnetization dynamics of irradiation-fabricated perpendicularly magnetized dots inside a softer magnetic matrix

2003 ◽  
Vol 777 ◽  
Author(s):  
T. Devolder ◽  
M. Belmeguenai ◽  
C. Chappert ◽  
H. Bernas ◽  
Y. Suzuki
Keyword(s):  
Domain Wall ◽  
Magnetic Anisotropy ◽  
Magnetization Reversal ◽  
Ion Irradiation ◽  
Magnetic Nanostructures ◽  
Magnetic Storage ◽  
Exchange Field ◽  
Static Magnetization ◽  
Specific Domain ◽  
Helium Ion

AbstractGlobal Helium ion irradiation can tune the magnetic properties of thin films, notably their magneto-crystalline anisotropy. Helium ion irradiation through nanofabricated masks can been used to produce sub-micron planar magnetic nanostructures of various types. Among these, perpendicularly magnetized dots in a matrix of weaker magnetic anisotropy are of special interest because their quasi-static magnetization reversal is nucleation-free and proceeds by a very specific domain wall injection from the magnetically “soft” matrix, which acts as a domain wall reservoir for the “hard” dot. This guarantees a remarkably weak coercivity dispersion. This new type of irradiation-fabricated magnetic device can also be designed to achieve high magnetic switching speeds, typically below 100 ps at a moderate applied field cost. The speed is obtained through the use of a very high effective magnetic field, and high resulting precession frequencies. During magnetization reversal, the effective field incorporates a significant exchange field, storing energy in the form of a domain wall surrounding a high magnetic anisotropy nanostructure's region of interest. The exchange field accelerates the reversal and lowers the cost in reversal field. Promising applications to magnetic storage are anticipated.

Color Space Transformation using Neural Networks

2019 ◽  
Vol 2019 (1) ◽  
pp. 153-158
Author(s):  
Lindsay MacDonald
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Color Space ◽  
Reflectance Spectra ◽  
Network Architectures ◽  
Color Spaces ◽  
Natural Materials ◽  
Space Transformation ◽  
Color Space Transformation

We investigated how well a multilayer neural network could implement the mapping between two trichromatic color spaces, specifically from camera R,G,B to tristimulus X,Y,Z. For training the network, a set of 800,000 synthetic reflectance spectra was generated. For testing the network, a set of 8,714 real reflectance spectra was collated from instrumental measurements on textiles, paints and natural materials. Various network architectures were tested, with both linear and sigmoidal activations. Results show that over 85% of all test samples had color errors of less than 1.0 ΔE2000 units, much more accurate than could be achieved by regression.

Estimating Pigment Concentrations from Spectral Images Using an Encoder‐Decoder Neural Network

2020 ◽  
Vol 64 (3) ◽  
pp. 30502-1-30502-15
Author(s):  
Kensuke Fukumoto ◽  
Norimichi Tsumura ◽  
Roy Berns
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Absorption Coefficient ◽  
Spectral Data ◽  
High Accuracy ◽  
Pigment Concentration ◽  
Scattering Coefficient ◽  
A Value ◽  
Input And Output ◽  
Pigment Concentrations

Abstract A method is proposed to estimate the concentration of pigments mixed in a painting, using the encoder‐decoder model of neural networks. The model is trained to output a value that is the same as its input, and its middle output extracts a certain feature as compressed information about the input. In this instance, the input and output are spectral data of a painting. The model is trained with pigment concentration as the middle output. A dataset containing the scattering coefficient and absorption coefficient of each of 19 pigments was used. The Kubelka‐Munk theory was applied to the coefficients to obtain many patterns of synthetic spectral data, which were used for training. The proposed method was tested using spectral images of 33 paintings, which showed that the method estimates, with high accuracy, the concentrations that have a similar spectrum of the target pigments.

Neural Network Techniques for Time Series Prediction: A Review

2019 ◽  
Vol 3 (3) ◽  
Author(s):  
Muhammad Faheem Mushtaq ◽  
Urooj Akram ◽  
Muhammad Aamir ◽  
Haseeb Ali ◽  
Muhammad Zulqarnain
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Time Series Data ◽  
Weather Prediction ◽  
Time Series Prediction ◽  
Series Data ◽  
Prediction Problem ◽  
Neural Network Models ◽  
Physical Time

It is important to predict a time series because many problems that are related to prediction such as health prediction problem, climate change prediction problem and weather prediction problem include a time component. To solve the time series prediction problem various techniques have been developed over many years to enhance the accuracy of forecasting. This paper presents a review of the prediction of physical time series applications using the neural network models. Neural Networks (NN) have appeared as an effective tool for forecasting of time series.  Moreover, to resolve the problems related to time series data, there is a need of network with single layer trainable weights that is Higher Order Neural Network (HONN) which can perform nonlinearity mapping of input-output. So, the developers are focusing on HONN that has been recently considered to develop the input representation spaces broadly. The HONN model has the ability of functional mapping which determined through some time series problems and it shows the more benefits as compared to conventional Artificial Neural Networks (ANN). The goal of this research is to present the reader awareness about HONN for physical time series prediction, to highlight some benefits and challenges using HONN.

Neural networks approached for modelling river suspended sediment concentration due to tropical storms

2013 ◽  
Vol 11 (4) ◽  
pp. 457-466
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Suspended Sediment ◽  
Suspended Sediment Concentration ◽  
Time Series Data ◽  
Water Discharge ◽  
Sediment Concentration ◽  
Series Data ◽  
Generalized Regression Neural Network ◽  
Event Based

Artificial neural networks are one of the advanced technologies employed in hydrology modelling. This paper investigates the potential of two algorithm networks, the feed forward backpropagation (BP) and generalized regression neural network (GRNN) in comparison with the classical regression for modelling the event-based suspended sediment concentration at Jiasian diversion weir in Southern Taiwan. For this study, the hourly time series data comprised of water discharge, turbidity and suspended sediment concentration during the storm events in the year of 2002 are taken into account in the models. The statistical performances comparison showed that both BP and GRNN are superior to the classical regression in the weir sediment modelling. Additionally, the turbidity was found to be a dominant input variable over the water discharge for suspended sediment concentration estimation. Statistically, both neural network models can be successfully applied for the event-based suspended sediment concentration modelling in the weir studied herein when few data are available.

Squeak and rattle noise classification using radial basis function neural networks

2020 ◽  
Vol 68 (4) ◽  
pp. 283-293
Author(s):  
Oleksandr Pogorilyi ◽  
Mohammad Fard ◽  
John Davy ◽  
Mechanical and Automotive Engineering, School ◽  
Mechanical and Automotive Engineering, School ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Accuracy ◽  
Training Method ◽  
Vehicle Interior ◽  
Trained Classifier ◽  
Different Types ◽  
Noise Classification ◽  
Automatic Tool ◽  
Multi Class Classification

In this article, an artificial neural network is proposed to classify short audio sequences of squeak and rattle (S&R) noises. The aim of the classification is to see how accurately the trained classifier can recognize different types of S&R sounds. Having a high accuracy model that can recognize audible S&R noises could help to build an automatic tool able to identify unpleasant vehicle interior sounds in a matter of seconds from a short audio recording of the sounds. In this article, the training method of the classifier is proposed, and the results show that the trained model can identify various classes of S&R noises: simple (binary clas- sification) and complex ones (multi class classification).

Operational Determination of the Activated Sludge Process Using Neural Networks

1992 ◽  
Vol 26 (9-11) ◽  
pp. 2461-2464 ◽  
Author(s):  
R. D. Tyagi ◽  
Y. G. Du
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Steady State ◽  
Activated Sludge ◽  
Feedforward Neural Network ◽  
Training Data ◽  
Activated Sludge Process

A steady-statemathematical model of an activated sludgeprocess with a secondary settler was developed. With a limited number of training data samples obtained from the simulation at steady state, a feedforward neural network was established which exhibits an excellent capability for the operational prediction and determination.

Real-time Detection of Aortic Valve in Echocardiography using Convolutional Neural Networks

2020 ◽  
Vol 16 (5) ◽  
pp. 584-591 ◽  
Author(s):  
Muhammad Hanif Ahmad Nizar ◽  
Chow Khuen Chan ◽  
Azira Khalil ◽  
Ahmad Khairuddin Mohamed Yusof ◽  
Khin Wee Lai
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Heart Disease ◽  
Aortic Valve ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Valvular Heart Disease ◽  
Detection System ◽  
Processing Unit ◽  
Real Time Detection

Background: Valvular heart disease is a serious disease leading to mortality and increasing medical care cost. The aortic valve is the most common valve affected by this disease. Doctors rely on echocardiogram for diagnosing and evaluating valvular heart disease. However, the images from echocardiogram are poor in comparison to Computerized Tomography and Magnetic Resonance Imaging scan. This study proposes the development of Convolutional Neural Networks (CNN) that can function optimally during a live echocardiographic examination for detection of the aortic valve. An automated detection system in an echocardiogram will improve the accuracy of medical diagnosis and can provide further medical analysis from the resulting detection. Methods: Two detection architectures, Single Shot Multibox Detector (SSD) and Faster Regional based Convolutional Neural Network (R-CNN) with various feature extractors were trained on echocardiography images from 33 patients. Thereafter, the models were tested on 10 echocardiography videos. Results: Faster R-CNN Inception v2 had shown the highest accuracy (98.6%) followed closely by SSD Mobilenet v2. In terms of speed, SSD Mobilenet v2 resulted in a loss of 46.81% in framesper- second (fps) during real-time detection but managed to perform better than the other neural network models. Additionally, SSD Mobilenet v2 used the least amount of Graphic Processing Unit (GPU) but the Central Processing Unit (CPU) usage was relatively similar throughout all models. Conclusion: Our findings provide a foundation for implementing a convolutional detection system to echocardiography for medical purposes.

Sign in / Sign up

Export Citation Format

Share Document