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.

Estimation of Site Amplification from Geotechnical Array Data Using Neural Networks

2021 ◽  
Author(s):  
Daniel Roten ◽  
Kim B. Olsen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Site Response ◽  
Site Amplification ◽  
Data Driven ◽  
Vertical Array ◽  
The Neural Network ◽  
Simplifying Assumptions ◽  
The Mean ◽  
Fully Connected

ABSTRACT We use deep learning to predict surface-to-borehole Fourier amplification functions (AFs) from discretized shear-wave velocity profiles. Specifically, we train a fully connected neural network and a convolutional neural network using mean AFs observed at ∼600 KiK-net vertical array sites. Compared with predictions based on theoretical SH 1D amplifications, the neural network (NN) results in up to 50% reduction of the mean squared log error between predictions and observations at sites not used for training. In the future, NNs may lead to a purely data-driven prediction of site response that is independent of proxies or simplifying assumptions.

scholarly journals Adaptation of the Diagnostic Artificial Neural Network Structure When New Training Examples Appear

2020 ◽  
Vol 6 (4) ◽  
pp. 120-126
Author(s):  
A. Malikov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Information Security ◽  
Classification Problem ◽  
Data Set ◽  
Neural Network Structure ◽  
Artificial Neural ◽  
Training Examples ◽  
Information Image

In this paper we can see that identified computer incidents are subject for diagnostics, during which the characteristics of information security violations are clarified (purpose, causes, consequences, etc.). To diagnose computer incidents, we can use methods of automation while collection and processing the events that occur as a result of the implementation of scenarios for information security violations. Artificial neural networks can be used to solve the classification problem of assigning diagnostic data set (information image of a computer incident) to one of the possible values of the violation characteristic. The purpose of this work is to adapt the structure of an artificial neural network that allows the accuracy diagnostics of computer incidents when new training examples appear.

scholarly journals NEURAL NETWORK ANALYSIS FOR TUMOR INVESTIGATION AND CANCER PREDICTION

2019 ◽  
Vol 2019 (02) ◽  
pp. 89-98
Author(s):  
Vijayakumar T
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Early Stage ◽  
Original Data ◽  
Data Set ◽  
Cancer Prediction ◽  
The Neural Network ◽  
Feed Forward Neural Networks ◽  
The Neural Networks ◽  
Human Nervous System

Predicting the category of tumors and the types of the cancer in its early stage remains as a very essential process to identify depth of the disease and treatment available for it. The neural network that functions similar to the human nervous system is widely utilized in the tumor investigation and the cancer prediction. The paper presents the analysis of the performance of the neural networks such as the, FNN (Feed Forward Neural Networks), RNN (Recurrent Neural Networks) and the CNN (Convolutional Neural Network) investigating the tumors and predicting the cancer. The results obtained by evaluating the neural networks on the breast cancer Wisconsin original data set shows that the CNN provides 43 % better prediction than the FNN and 25% better prediction than the RNN.

scholarly journals ForkDec: Accurate Detection for Selfish Mining Attacks

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Zhaojie Wang ◽  
Qingzhe Lv ◽  
Zhaobo Lu ◽  
Yilei Wang ◽  
Shengjie Yue
Keyword(s):  
Neural Network ◽  
Incentive Mechanism ◽  
Attack Detection ◽  
Detection Accuracy ◽  
Data Set ◽  
Incentive Compatible ◽  
The Neural Network ◽  
Security Challenges ◽  
Excellent Research ◽  
Fully Connected

Incentive mechanism is the key to the success of the Bitcoin system as a permissionless blockchain. It encourages participants to contribute their computing resources to ensure the correctness and consistency of user transaction records. Selfish mining attacks, however, prove that Bitcoin’s incentive mechanism is not incentive-compatible, which is contrary to traditional views. Selfish mining attacks may cause the loss of mining power, especially those of honest participants, which brings great security challenges to the Bitcoin system. Although there are a series of studies against selfish mining behaviors, these works have certain limitations: either the existing protocol needs to be modified or the detection effect for attacks is not satisfactory. We propose the ForkDec, a high-accuracy system for selfish mining detection based on the fully connected neural network, for the purpose of effectively deterring selfish attackers. The neural network contains a total of 100 neurons (10 hidden layers and 10 neurons per layer), learned on a training set containing about 200,000 fork samples. The data set, used to train the model, is generated by a Bitcoin mining simulator that we preconstructed. We also applied ForkDec to the test set to evaluate the attack detection and achieved a detection accuracy of 99.03%. The evaluation experiment demonstrates that ForkDec has certain application value and excellent research prospects.

scholarly journals Neural network based approximation of muscle and joint contact forces during jumping and landing

2019 ◽  
Author(s):  
Daniel Cleather
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real Time ◽  
Contact Forces ◽  
Data Set ◽  
Video Record ◽  
Musculoskeletal Models ◽  
The Neural Network ◽  
Joint Contact ◽  
The Neural Networks

Musculoskeletal models have been used to estimate the muscle and joint contact forces expressed during movement. One limitation of this approach, however, is that such models are computationally demanding, which limits the possibility of using them for real-time feedback. One solution to this problem is to train a neural network to approximate the performance of the model, and then to use the neural network to give real-time feedback. In this study, neural networks were trained to approximate the FreeBody musculoskeletal model for jumping and landing tasks. The neural networks were better able to approximate jumping than landing, which was probably a result of the greater variability in the landing data set used in this study. In addition, a neural network that was based on a reduced set of inputs was also trained to approximate the outputs of FreeBody during a landing task. These results demonstrate the feasibility of using neural networks to approximate the results of musculoskeletal models in order to provide real-time feedback. In addition, these neural networks could be based upon a reduced set of kinematic variables taken from a 2-dimensional video record, making the implementation of mobile applications a possibility.

scholarly journals Recognition of wavefront aberrations types corresponding to single Zernike functions from the pattern of the point spread function in the focal plane using neural networks

2020 ◽  
Vol 44 (6) ◽  
pp. 923-930
Author(s):  
I.A. Rodin ◽  
S.N. Khonina ◽  
P.G. Serafimovich ◽  
S.B. Popov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Point Spread Function ◽  
Focal Plane ◽  
Prediction Errors ◽  
Intensity Pattern ◽  
Data Set ◽  
Point Spread ◽  
The Neural Network ◽  
Spread Function

In this work, we carried out training and recognition of the types of aberrations corresponding to single Zernike functions, based on the intensity pattern of the point spread function (PSF) using convolutional neural networks. PSF intensity patterns in the focal plane were modeled using a fast Fourier transform algorithm. When training a neural network, the learning coefficient and the number of epochs for a dataset of a given size were selected empirically. The average prediction errors of the neural network for each type of aberration were obtained for a set of 15 Zernike functions from a data set of 15 thousand PSF pictures. As a result of training, for most types of aberrations, averaged absolute errors were obtained in the range of 0.012 – 0.015. However, determining the aberration coefficient (magnitude) requires additional research and data, for example, calculating the PSF in the extrafocal plane.

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.

Varіatіons іn the predіctіve effіcіency of soіl maps dependіng on the methods of constructіng traіnіng samples of predіcatіve algorіthms

2017 ◽  
Vol 28 (3-4) ◽  
pp. 55-71
Author(s):  
V. R. Cherlіnka
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Random Forests ◽  
Land Surface ◽  
Free Software ◽  
Support Vector ◽  
Data Set ◽  
Surface Parameters ◽  
The Neural Network ◽  
Land Surface Parameters

The maіn objectіve was to study the іnfluence of the traіnіng dataset on the qualіtatіve characterіstіcs of sіmulatіve soіl maps, whіch are obtaіned through sіmulatіon usіng a typіcal set of materіals that can be potentіally avaіlable for the soіl scіentіst іn modern Ukraіnіan realіtіes. Achіevement of thіs goal was achіeved by solvіng a number of the followіng tasks: a) dіgіtіzіng of cartographіc materіals; b) creatіng DEM wіth a resolutіon equal to 10 m; c) analysіs of dіgіtal elevatіon models and extractіon of land surface parameters; d) generatіon of traіnіng datasets accordіng to the descrіbed methodologіcal approaches; e) creatіon sіmulatіon models of soіl-cover іn R-statіstіc; g) analysіs of the obtaіned results and conclusіons regardіng the optіmal sіze of the traіnіng datasets for predіctіve modelіng of the soіl cover and іts duratіon. As an object was selected a fragment of the terrіtory of Ukraіne (4200×4200 m) wіthіn the lіmіts of Glybotsky dіstrіct of the Chernіvtsі regіon, confіned to the Prut-Sіret іnterfluve (North Bukovyna) wіth contrast geomorphologіcal condіtіons. Thіs area has dіfferent admіnіstratіve subordіnatіon and economіc use but іs covered wіth soіl cartographіc materіals only by 49.43 %. For data processіng were used іnstrumental possіbіlіtіes of free software: geo- rectіfіcatіons of maps materіal – GІS Quantum, dіgіtalіzatіon – Easy Trace, preparatіon of maps morphometrіc parameters – GRASS GІS and buіldіng sіmulatіve soіl maps – R, a language and envіronment for statіstіcal computіng. To create sіmulatіon models of soіl cover, a R-statіstіc scrіpt was wrіtten that іncludes a number of adaptatіons for solvіng set tasks and іmplements the dіfferent types of predіcatіve algorіthms such as: Multіnomіal Logіstіc Regressіon, Decіsіon Trees, Neural Networks, Random Forests, K-Nearest Neіghbors, Support Vector Machіnes and Bagged Trees. To assess the qualіty of the obtaіned models, the Cohen’s Kappa Іndex (?) was used whіch best represents the degree of complіance between the orіgіnal and the sіmulated data. As a benchmark, the usual medіal axes traіnіng dataset of was used. Other study optіons were: medіan-weіghted and randomіzed-weіghted samplіng. Thіs together wіth 7 predіcatіve algorіthms allowed to get 72 soіl sіmulatіons, the analysіs of whіch revealed quіte іnterestіng patterns. Models rankіng by іncreasіng the qualіty of the predіctіon by the kappa of the maіn data set shown, that the MLR algorіthm showed the worst results among others. Next іn ascendіng order are Neural Network, SVM, KNN, BGT, RF, DT. The last three algorіthms refer to the classіfіcatіon and theіr hіgh results іndіcate the greatest suіtabіlіty of such approaches іn sіmulatіon of soіl cover. The sample based on the weіghted medіan dіd not show strong advantages over others, as the results are quіte controversіal. Only іn the case of the neural network and the Bugget Trees the results of the medіan-weіghted sample predіctіon showed a better result vs a sіmple medіan sample and much worse than any varіants of randomіzed traіnіng data. Other algorіthms requіred a dіfferent number of randomіzed poіnts to cross the 90 % kappa: KNN – 25 %; BGT, RF and DT – 90 %. To achіeve 95 % kappa BGT algorіthm requіres 30% traіnіng poіnts of the total, RF – 25 % and DT – 20 %. Decіsіon Trees as a result turned out to be the most powerful algorіthm, whіch was able to sіmulate the dіstrіbutіon of soіl abnormalіtіes from kappa 97.13 % wіth 35 % saturatіon of the traіnіng sample wіth the orіgіnal data. Overall, DT shows a great dіfference between the approaches to selectіng traіnіng data: any medіan falls by 13 % іn front of a sіmple 5 % randomіzed-weіghted set of traіnіng cells and 22 % – about 35 % of the set.

scholarly journals Classification of Plant Leaf Diseases Based on Improved Convolutional Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4161 ◽  
Author(s):  
Hang ◽  
Zhang ◽  
Chen ◽  
Zhang ◽  
Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Convergence Time ◽  
Model Parameters ◽  
Data Set ◽  
Training Time ◽  
Plant Leaf ◽  
The Neural Network ◽  
Target Disease ◽  
Fully Connected

Plant leaf diseases are closely related to people's daily life. Due to the wide variety of diseases, it is not only time-consuming and labor-intensive to identify and classify diseases by artificial eyes, but also easy to be misidentified with having a high error rate. Therefore, we proposed a deep learning-based method to identify and classify plant leaf diseases. The proposed method can take the advantages of the neural network to extract the characteristics of diseased parts, and thus to classify target disease areas. To address the issues of long training convergence time and too-large model parameters, the traditional convolutional neural network was improved by combining a structure of inception module, a squeeze-and-excitation (SE) module and a global pooling layer to identify diseases. Through the Inception structure, the feature data of the convolutional layer were fused in multi-scales to improve the accuracy on the leaf disease dataset. Finally, the global average pooling layer was used instead of the fully connected layer to reduce the number of model parameters. Compared with some traditional convolutional neural networks, our model yielded better performance and achieved an accuracy of 91.7% on the test data set. At the same time, the number of model parameters and training time have also been greatly reduced. The experimental classification on plant leaf diseases indicated that our method is feasible and effective.

scholarly journals A Comparative Study of Neural Networks and Fuzzy Systems in Modeling of a Nonlinear Dynamic System

2011 ◽  
Vol 1 (1) ◽  
pp. 65-73 ◽  
Author(s):  
Metin DEMIRTAS ◽  
Musa ALCI
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fuzzy Systems ◽  
Performance Modeling ◽  
Nonlinear Dynamic System ◽  
Predictive Performance ◽  
Model Parameters ◽  
Data Set ◽  
The Neural Network ◽  
Practical Performance

The aim of this paper is to compare the neural network and fuzzy modeling approaches on a nonlinear system. We have taken Permanent Magnet Brushless Direct Current (PMBDC) motor data and have generated models using both approaches. The predictive performance of both methods was compared on the data set for model configurations.The paper describes the results of these tests and discusses the effects of changing model parameters on predictive and practical performance. Modeling sensitivity was used to compare for two methods. 

Sign in / Sign up

Export Citation Format

Share Document