• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.19-31
• /
• 2022

In Machine learning, we usually divide the entire data into training data and test data, train the model using training data, and use test data to determine the accuracy and generalization performance of the model. In the case of models with low generalization performance, the prediction accuracy of newly data is significantly reduced, and the model is said to be overfit. This study is about a method of generating training data based on central limit theorem and combining it with existed training data to increase normality and using this data to train models and increase generalization performance. To this, data were generated using sample mean and standard deviation for each feature of the data by utilizing the characteristic of central limit theorem, and new training data was constructed by combining them with existed training data. To determine the degree of increase in normality, the Kolmogorov-Smirnov normality test was conducted, and it was confirmed that the new training data showed increased normality compared to the existed data. Generalization performance was measured through differences in prediction accuracy for training data and test data. As a result of measuring the degree of increase in generalization performance by applying this to K-Nearest Neighbors (KNN), Logistic Regression, and Linear Discriminant Analysis (LDA), it was confirmed that generalization performance was improved for KNN, a non-parametric technique, and LDA, which assumes normality between model building.

• School Mathematics
• /
• v.14 no.3
• /
• pp.357-375
• /
• 2012

This research intends to examine how 6th graders (age 12) generalize various increasing patterns. In this research, 6 problems corresponding to the ax, x+a, ax+c, ax2, and ax2+c patterns were given to 290 students. Students' generalization methods were analysed by the generalization level suggested by Radford(2006), such as arithmetic and algebraic (factual, contextual, and symbolic) generalization. As the results of the study, we identified that students revealed the most high performance in the ax pattern in the aspect of the algebraic generalization, and lower performance in the ax2, x+a, ax+c, ax2+c in order. Also we identified that students' generalization methods differed in the same increasing patterns. This imply that we need to provide students with the pattern generalization activities in various contexts.

• Journal of the Korean Mathematical Society
• /
• v.59 no.2
• /
• pp.217-233
• /
• 2022

Although machine learning shows state-of-the-art performance in a variety of fields, it is short a theoretical understanding of how machine learning works. Recently, theoretical approaches are actively being studied, and there are results for one of them, margin and its distribution. In this paper, especially we focused on the role of margin in the perturbations of inputs and parameters. We show a generalization bound for two cases, a linear model for binary classification and neural networks for multi-classification, when the inputs have normal distributed random noises. The additional generalization term caused by random noises is related to margin and exponentially inversely proportional to the noise level for binary classification. And in neural networks, the additional generalization term depends on (input dimension) × (norms of input and weights). For these results, we used the PAC-Bayesian framework. This paper is considering random noises and margin together, and it will be helpful to a better understanding of model sensitivity and the construction of robust generalization.

• The KIPS Transactions:PartD
• /
• v.9D no.4
• /
• pp.543-554
• /
• 2002

GIS (Geographic Information Systems) need faster access and better visualization. For faster access and better visualization in GIS, map generalization and levels of detail are needed. Existing spatial indexing methods do not support map generalization. Also, a few existing spatial indexing methods supporting map generalization do not support ail map generalization operations. We propose a new index structure, i.e. the LR-tree, supporting ail map generalization operations. This paper presents algorithms for the searching and updating the LR-tree and the results of performance evaluation. Our index structure works better than other spatial indexing methods for map generalization.

• Phonetics and Speech Sciences
• /
• v.15 no.3
• /
• pp.83-88
• /
• 2023

This study investigates the fine-tuning of large-scale Automatic Speech Recognition (ASR) models, specifically OpenAI's Whisper model, for domain-specific applications using the KsponSpeech dataset. The primary research questions address the effectiveness of targeted lexical item emphasis during fine-tuning, its impact on domain-specific performance, and whether the fine-tuned model can maintain generalization capabilities across different languages and environments. Experiments were conducted using two fine-tuning datasets: Set A, a small subset emphasizing specific lexical items, and Set B, consisting of the entire KsponSpeech dataset. Results showed that fine-tuning with targeted lexical items increased recognition accuracy and improved domain-specific performance, with generalization capabilities maintained when fine-tuned with a smaller dataset. For noisier environments, a trade-off between specificity and generalization capabilities was observed. This study highlights the potential of fine-tuning using minimal domain-specific data to achieve satisfactory results, emphasizing the importance of balancing specialization and generalization for ASR models. Future research could explore different fine-tuning strategies and novel technologies such as prompting to further enhance large-scale ASR models' domain-specific performance.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.225-232
• /
• 2021

Deraining is one of the image restoration tasks and should consider a tradeoff between local details and broad contextual information while recovering images. Current studies adopt an attention mechanism which has been actively researched in natural language processing to deal with both global and local features. This paper classifies existing deraining methods and provides comparative analysis and performance comparison by using several datasets in terms of generalization.

• Journal of Korea Spatial Information System Society
• /
• v.6 no.2 s.12
• /
• pp.15-22
• /
• 2004

Map services for cellular phone have problem for implementation, which are the limitation of a screen size. To effectively represent map data on screen of celluar phone, it need a process which translate a detailed map data into less detailed data using map generalization, and it should manipulate zoom in out quickly by leveling the generalized data. However, current spatial indexing methods supporting map generalization do not support all map generalization operations. In this paper, We propose a leveled spatial indexing method, LMG-tree, supporting map generalization and presents the results of performance evaluation.

• Journal of Advanced Marine Engineering and Technology
• /
• v.21 no.1
• /
• pp.66-70
• /
• 1997

In this paper a new learning algorithm for curvature smoothing and improved generalization for multi-layer neural networks is proposed. To enhance the generalization ability a constraint term of hidden neuron activations is added to the conventional output error, which gives the curvature smoothing characteristics to multi-layer neural networks. When the total cost consisted of the output error and hidden error is minimized by gradient-descent methods, the additional descent term gives not only the Hebbian learning but also the synaptic weight decay. Therefore it incorporates error back-propagation, Hebbian, and weight decay, and additional computational requirements to the standard error back-propagation is negligible. From the computer simulation of the time series prediction with Santafe competition data it is shown that the proposed learning algorithm gives much better generalization performance.

• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.537-542
• /
• 2004

Multi-Layer Perceptron network has been mainly applied to many practical problems because of its nonlinear mapping ability. However the generalization ability of MLP networks may be affected by the number of hidden nodes, the initial values of weights and the training errors. These factors, if improperly chosen, may result in poor generalization ability of MLP networks. It is important to identify these factors and their interaction in order to control effectively the generalization ability of MLP networks. In this paper, we have empirically identified the factors that affect the generalization ability of MLP networks, and compared their relative effects on the generalization performance for the conventional and visualized weight selecting methods using the controller box.

• Journal of Korea Society of Industrial Information Systems
• /
• v.10 no.1
• /
• pp.28-37
• /
• 2005

In our previous works, we suggested a method that extracts representative keywords from a few positive documents and assigns weights to them. To show the usefulness of the method, in this paper, we evaluate the performance of a famous classification algorithm called GIS(Generalized Instance Set) when it is combined with our method. In GIS algorithm, generalized instances are built from learning documents by a generalization function and then the K-NN algorithm is applied to them. Here, our method is used as a generalization function. For comparative works, Rocchio and Widrow-Hoff algorithms are also used as a generalization function. Experimental results show that our method is better than the others for the case that only positive documents are considered, but not when negative documents are considered together.