• ETRI Journal
• /
• v.32 no.3
• /
• pp.486-489
• /
• 2010

This letter presents a modified Pegasos algorithm for graph-based dependency parsing. We show that the modified Pegasos algorithm outperforms the margin infused relaxed and passive aggressive algorithms in three languages.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.152-159
• /
• 2005

For high-speed data communication in band-limited channels, main of the bit error are fading and ISI(Inter-Symbol Interference). The common way of dealing with ISI is using equalization in the receiver. In this thesis, channel adaptive equalizer which uses Fuzzy Stochastic Gradient(FSG) and Constant Modulus Algorithm(CMA) is nonlinear equalizer, or Blind equalizer, that works directly on the signals with no training sequences required. This equalizer employs Takagi-Sugeno's fuzzy model that uses the FSG algorithm, to automatically regulate the step size of the descent gradient vector, combining fast convergence rate and low mean square error(MSE), and the CMA which is a special case of Godard's algorithm, to having multiple dispersion constants($R_p$).

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.352-358
• /
• 2022

Text mining is an important process used for analyzing the data collected from different sources like videos, audio, social media, and so on. The tools like Natural Language Processing (NLP) are mostly used in real-time applications. In the earlier research, text mining approaches were implemented using long-short memory (LSTM) networks. In this paper, text mining is performed using average-stochastic gradient descent weight-dropped (AWD)-LSTM techniques to obtain better accuracy and performance. The proposed model is effectively demonstrated by considering the internet movie database (IMDB) reviews. To implement the proposed model Python language was used due to easy adaptability and flexibility while dealing with massive data sets/databases. From the results, it is seen that the proposed LSTM plus weight dropped plus embedding model demonstrated an accuracy of 88.36% as compared to the previous models of AWD LSTM as 85.64. This result proved to be far better when compared with the results obtained by just LSTM model (with 85.16%) accuracy. Finally, the loss function proved to decrease from 0.341 to 0.299 using the proposed model

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.87-92
• /
• 2021

Bias, variance, error and learning are important factors for performance in modeling a big data based recommendation system. The recommendation model in this system must reduce complexity while maintaining the explanatory diagram. In addition, the sparsity of the dataset and the prediction of the system are more likely to be inversely proportional to each other. Therefore, a product recommendation model has been proposed through learning the similarity between products by using a factorization method of the sparsity of the dataset. In this paper, the generalization ability of the model is improved by applying the max-norm regularization as an optimization method for the loss function of this model. The solution is to apply a stochastic projection gradient descent method that projects a gradient. The sparser data became, it was confirmed that the propsed regularization method was relatively effective compared to the existing method through lots of experiment.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3519-3533
• /
• 2020

Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What's more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.145-154
• /
• 1994

This paper proposes an efficient method for improving the training performance of the neural network by using a hybrid of a stochastic approximation and a backpropagation algorithm. The proposed method improves the performance of the training by appliying a global optimization method which is a hybrid of a stochastic approximation and a backpropagation algorithm. The approximate initial point for a stochastic approximation and a backpropagation algorihtm. The approximate initial point for fast global optimization is estimated first by applying the stochastic approximation, and then the backpropagation algorithm, which is the fast gradient descent method, is applied for a high speed global optimization. And further speed-up of training is made possible by adjusting the training parameters of each of the output and the hidden layer adaptively to the standard deviation of the neuron output of each layer. The proposed method has been applied to the parity checking and the pattern classification, and the simulation results show that the performance of the proposed method is superior to that of the backpropagation, the Baba's MROM, and the Sun's method with randomized initial point settings. The results of adaptive adjusting of the training parameters show that the proposed method further improves the convergence speed about 20% in training.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.3
• /
• pp.79-89
• /
• 1998

The Error Back-Propagation(EBP) algorithm is widely applied to train a multi-layer perceptron, which is a neural network model frequently used to solve complex problems such as pattern recognition, adaptive control, and global optimization. However, the EBP is basically a gradient descent method, which may get stuck in a local minimum, leading to failure in finding the globally optimal solution. Moreover, a multi-layer perceptron suffers from locking a systematic determination of the network structure appropriate for a given problem. It is usually the case to determine the number of hidden nodes by trial and error. In this paper, we propose a new algorithm to efficiently train a multi-layer perceptron. OUr algorithm uses stochastic perturbation in the weight space to effectively escape from local minima in multi-layer perceptron learning. Stochastic perturbation probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the probabilistically re-initializes weights associated with hidden nodes to escape a local minimum if the EGP learning gets stuck to it. Addition of new hidden nodes also can be viewed asa special case of stochastic perturbation. Using stochastic perturbation we can solve the local minima problem and the network structure design in a unified way. The results of our experiments with several benchmark test problems including theparity problem, the two-spirals problem, andthe credit-screening data show that our algorithm is very efficient.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.1015-1025
• /
• 2017

Bayesian personalized ranking (BPR) is a state-of-the-art recommendation system techniques for implicit feedback data. Unfortunately, there might be a loss of information because the BPR model considers only the binary transformation of implicit feedback that is non-binary data in most cases. We propose a modified BPR method using a level of confidence based on the size or strength of implicit feedback to overcome this limitation. The proposed method is useful because it still has a structure of interpretable models for underlying personalized ranking i.e., personal pairwise preferences as in the BPR and that it is capable to reflect a numerical size or the strength of implicit feedback. We propose a computation algorithm based on stochastic gradient descent for the numerical implementation of our proposal. Furthermore, we also show the usefulness of our proposed method compared to ordinary BPR via an analysis of steam video games data.