scholarly journals THE IMPLEMENTATION OF THE NEURAL NETWORK FOR THE CLASSIFICATION PROBLEM

2014 ◽  
pp. 119-126
Author(s):  
Ulyana Lisovik ◽  
Oleksandr Lipchanskiy
Keyword(s):  
Neural Network ◽  
Structural Model ◽  
Classification Problem ◽  
Model Description ◽  
Function Model ◽  
System Synthesis ◽  
The Neural Network ◽  
Hardware Costs ◽  
Vhdl Code ◽  
Characteristics Estimation

The example of NN realization is considered. Also description of all its design stages from NN function model description to its timing and hardware characteristics estimation is considered. NN structural model is presented in VHDL code. Through SynplifyPro 7.0 package from Synplicity® the system synthesis with the orientation on Virtex- II XC2V6000 family is made out. The estimation of the optimality of the synthesized NN model utilization is accomplished. NN structures are shown; hardware costs are taken to the table.

A Hybrid Modeling Technique for Partially-Known Systems Using Linear Regression and Neural Network

2009 ◽  
Author(s):  
Andrew J. Joslin ◽  
Chengying Xu
Keyword(s):  
Neural Network ◽  
Linear Regression ◽  
Least Squares ◽  
Process Model ◽  
Modeling Method ◽  
Hybrid Modeling ◽  
Model Description ◽  
Least Squares Regression ◽  
The Neural Network ◽  
Macro Scale

In this paper a hybrid modeling and system identification method, combining linear least squares regression and artificial neural network techniques, is presented to model a type of dynamic systems which have an incomplete analytical model description. This approach in modeling nonlinear, partially-understood systems is particularly useful to the study of manufacturing processes, where the linear regression portion of the hybrid model is established using a known mathematical model for the process and the neural network is constructed using the residuals from the least squares regression, therefore ensuring a more precise process model for the specific machining setup, tooling selection, workpiece properties, etc. In this paper the method is mathematically proven to give regression coefficients close to those which would be found if only a regression had been performed. The modeling method is then simulated for a macro-scale hard turning process, and the result proves the effectiveness of the proposed hybrid modeling method.

Endek Classification Based On GLCM Using Artificial Neural Networks with Adam Optimization

2020 ◽  
Vol 9 (2) ◽  
pp. 285
Author(s):  
Putu Wahyu Tirta Guna ◽  
Luh Arida Ayu Ayu Rahning Putri
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Back Propagation ◽  
Classification Problem ◽  
Model Accuracy ◽  
Computing Power ◽  
The Neural Network ◽  
Extraction Algorithm ◽  
Better Than

Not many people know that endek cloth itself has 4 known variances. .Nowadays. Computing and classification algorithm can be implemented to solve classification problem with respect to the features data as input. We can use this computing power to digitalize these endek pattern. The features extraction algorithm used in this research is GLCM. Where these data will act as input for the neural network model later. There is a lot of optimizer algorithm to use in back propagation phase. In this research we  prefer to use adam which is one of the newest and most popular optimizer algorithm. To compare its performace we also use SGD which is older and popular optimizer algorithm. Later we find that adam algorithm generate 33% accuracy which is better than what SGD algorithm give, it is 23% accuracy. Longer epoch also give affect for overall model accuracy.

Calculation of Compressor Characteristics Based on Elman Neural Network

2012 ◽  
Vol 500 ◽  
pp. 727-732
Author(s):  
Yong Ming Feng ◽  
Dong Lai Zhao ◽  
Peng Qi Zhang
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Pressure Ratio ◽  
Axial Compressor ◽  
Good Precision ◽  
Function Model ◽  
Elman Neural Network ◽  
The Neural Network ◽  
Result Show

A calculation of an axial compressor characteristics is made based on Elman neural network. The experimental data provided by manufacturers are used for the neural network training.To establish the function model to obtain the pressure ratio and efficiency respectively. The result show that Elman neural network both have a good precision for prediction of interpolation and extrapolation.

scholarly journals Simplicial-Map Neural Networks Robust to Adversarial Examples

Mathematics ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 169
Author(s):  
Eduardo Paluzo-Hidalgo ◽  
Rocio Gonzalez-Diaz ◽  
Miguel A. Gutiérrez-Naranjo ◽  
Jónathan Heras
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Algebraic Topology ◽  
Classification Problem ◽  
Classification Model ◽  
The Neural Network ◽  
Input Dataset ◽  
Adversarial Examples ◽  
Simplicial Map ◽  
Adversarial Example

Broadly speaking, an adversarial example against a classification model occurs when a small perturbation on an input data point produces a change on the output label assigned by the model. Such adversarial examples represent a weakness for the safety of neural network applications, and many different solutions have been proposed for minimizing their effects. In this paper, we propose a new approach by means of a family of neural networks called simplicial-map neural networks constructed from an Algebraic Topology perspective. Our proposal is based on three main ideas. Firstly, given a classification problem, both the input dataset and its set of one-hot labels will be endowed with simplicial complex structures, and a simplicial map between such complexes will be defined. Secondly, a neural network characterizing the classification problem will be built from such a simplicial map. Finally, by considering barycentric subdivisions of the simplicial complexes, a decision boundary will be computed to make the neural network robust to adversarial attacks of a given size.

scholarly journals The Integration of Linguistic and Geospatial Features Using Global Context Embedding for Automated Text Geocoding

2021 ◽  
Vol 10 (9) ◽  
pp. 572
Author(s):  
Zheren Yan ◽  
Can Yang ◽  
Lei Hu ◽  
Jing Zhao ◽  
Liangcun Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Classification Problem ◽  
Geographical Information ◽  
Local Context ◽  
Place Names ◽  
Global Features ◽  
Global Context ◽  
The Neural Network ◽  
Textual Data ◽  
Local And Global Features

Geocoding is an essential procedure in geographical information retrieval to associate place names with coordinates. Due to the inherent ambiguity of place names in natural language and the scarcity of place names in textual data, it is widely recognized that geocoding is challenging. Recent advances in deep learning have promoted the use of the neural network to improve the performance of geocoding. However, most of the existing approaches consider only the local context, e.g., neighboring words in a sentence, as opposed to the global context, e.g., the topic of the document. Lack of global information may have a severe impact on the robustness of the model. To fill the research gap, this paper proposes a novel global context embedding approach to generate linguistic and geospatial features through topic embedding and location embedding, respectively. A deep neural network called LGGeoCoder, which integrates local and global features, is developed to solve the geocoding as a classification problem. The experiments on a Wikipedia place name dataset demonstrate that LGGeoCoder achieves competitive performance compared with state-of-the-art models. Furthermore, the effect of introducing global linguistic and geospatial features in geocoding to alleviate the ambiguity and scarcity problem is discussed.

scholarly journals Early Stopping Criteria for Levenberg-Marquardt Based Neural Network Training Optimization

2018 ◽  
Vol 7 (4.36) ◽  
pp. 1194
Author(s):  
Azizah Suliman ◽  
Batyrkhan Omarov
Keyword(s):  
Neural Network ◽  
Classification Problem ◽  
Correct Choice ◽  
Network Training ◽  
The Neural Network ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Stop Condition ◽  
Hidden Neurons

In this research we train a direct distributed neural network using Levenberg-Marquardt algorithm. In order to prevent overtraining, we proposed correctly recognized image percentage based on early stop condition and conduct the experiments with different stop thresholds for image classification problem. Experiment results show that the best early stop condition is 93% and other increase in stop threshold can lead to decrease in the quality of the neural network. The correct choice of early stop condition can prevent overtraining which led to the training of a neural network with considerable number of hidden neurons.  

On Computer Memory Saving Methods in Performing Data Classification Using Fully Connected Neural Networks

Vestnik MEI ◽  
2021 ◽  
Vol 3 (3) ◽  
pp. 103-109
Author(s):  
Andrey I. Mamontov ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computing System ◽  
Classification Problem ◽  
Double Precision ◽  
Data Set ◽  
The Neural Network ◽  
Study Results ◽  
System Memory ◽  
Fully Connected

In solving the classification problem, a fully connected trainable neural network (with adjusting the parameters represented by double-precision real numbers) is used as a mathematical model. After the training is completed, the neural network parameters are rounded and represented as fixed-point numbers (integers). The aim of the study is to reduce the required amount of the computing system memory for storing the obtained integer parameters. To reduce the amount of memory, the following methods for storing integer parameters are developed, which are based on representing the linear polynomials included in a fully connected neural network using compositions of simpler functions: - a method based on representing the considered polynomial as a sum of simpler polynomials; - a method based on separately storing the information about additions and multiplications. In the experiment with the MNIST data set, it took 1.41 MB to store real parameters of a fully connected neural network, 0.7 MB to store integer parameters without using the proposed methods, 0.47 MB in the RAM and 0.3 MB in compressed form on the disk when using the first method, and 0.25 MB on the disk when using the second method. In the experiment with the USPS data set, it took 0.25 MB to store real parameters of a fully connected neural network, 0.1 MB to store integer parameters without using the proposed methods, 0.05 MB in the RAM and approximately the same amount in compressed form on the disk when using the first method, and 0.03 MB on the disk when using the second method. The study results can be applied in using fully connected neural networks to solve various recognition problems under the conditions of limited hardware capacities.

scholarly journals Palm Vein Identification Based on Vein Segmentation and Triplet Loss Function

2021 ◽  
Author(s):  
Denis Trofimov ◽  
Elena Pavelyeva
Keyword(s):  
Neural Network ◽  
Loss Function ◽  
Classification Problem ◽  
Similarity Learning ◽  
The Neural Network ◽  
Segmented Images ◽  
Neural Network Algorithm ◽  
Triplet Loss ◽  
Vein Recognition ◽  
Palm Vein

In this article the new neural network algorithm for palm vein identification using the triplet loss function is proposed. The neural network model is based on the VGG16 architecture. The similarity learning problem instead of the classification problem is considered. The number of image classes is assumed to be unknown so at the output of the neural network the feature vector is obtained, and then for the pair of palm vein images the distance between them is calculated. Minimization of triplet loss function while training leads to the decrease in distances between the images of the same class, while the distances between the images of different classes increase. The neural network was trained using preprocessed and segmented images from CASIA multi-spectral palmprint image database. The use of segmentation information for palm vein recognition improves the recognition results. Experimental results demonstrate the effectiveness of the proposed method. The value of EER=0.0084 is obtained.

Neural Network for Automatic Analysis of Motility Data

1994 ◽  
Vol 33 (01) ◽  
pp. 157-160 ◽  
Author(s):  
S. Kruse-Andersen ◽  
J. Kolberg ◽  
E. Jakobsen
Keyword(s):  
Neural Network ◽  
Muscular Activity ◽  
Recording System ◽  
Automatic Analysis ◽  
Biologically Relevant ◽  
System A ◽  
The Neural Network ◽  
Valuable Method ◽  
Motor Abnormalities ◽  
Trained Network

Abstract:Continuous recording of intraluminal pressures for extended periods of time is currently regarded as a valuable method for detection of esophageal motor abnormalities. A subsequent automatic analysis of the resulting motility data relies on strict mathematical criteria for recognition of pressure events. Due to great variation in events, this method often fails to detect biologically relevant pressure variations. We have tried to develop a new concept for recognition of pressure events based on a neural network. Pressures were recorded for over 23 hours in 29 normal volunteers by means of a portable data recording system. A number of pressure events and non-events were selected from 9 recordings and used for training the network. The performance of the trained network was then verified on recordings from the remaining 20 volunteers. The accuracy and sensitivity of the two systems were comparable. However, the neural network recognized pressure peaks clearly generated by muscular activity that had escaped detection by the conventional program. In conclusion, we believe that neu-rocomputing has potential advantages for automatic analysis of gastrointestinal motility data.

Sign in / Sign up

Export Citation Format

Share Document