• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.983-987
• /
• 2009

One of the critical themes in the language acquisition is its exposure to linguistic environments. Linguistic environments, which interact with infants, include not only human beings such as its parents but also artificially crafted linguistic media as their functioning elements. An infant learns a language by exploring these extensive language environments around it. Based on such large linguistic data exposure, we propose a machine learning based method on the cognitive mechanism that simulate flexibly and appropriately infant's language learning. The infant's initial stage of language learning comes with sentence learning and creation, which can be simulated by exposing it to a language corpus. The core of the simulation is a memory-based learning model which has language hypernetwork structure. The language hypernetwork simulates developmental and progressive language learning using the structure of new data stream through making it representing of high level connection between language components possible. In this paper, we simulates an infant's gradual and developmental learning progress by training language hypernetwork gradually using 32,744 sentences extracted from video scripts of commercial animation movies for children.

• International journal of advanced smart convergence
• /
• v.12 no.1
• /
• pp.70-75
• /
• 2023

With the recent proliferation of memory-intensive workloads such as deep learning, analyzing memory access characteristics for efficient memory management is becoming increasingly important. Since read and write operations in memory access have different characteristics, an efficient memory management policy should take into accountthe characteristics of thesetwo operationsseparately. Although some previous studies have considered the different characteristics of reads and writes, they require a modified hardware architecture supporting read bits and write bits. Unlike previous approaches, we propose a software-based management policy under the existing memory architecture for considering read/write characteristics. The proposed policy logically partitions memory space into the read/write area and the write area by making use of reference bits and dirty bits provided in modern paging systems. Simulation experiments with memory access traces show that our approach performs better than the CLOCK algorithm by 23% on average, and the effect is similar to the previous policy with hardware support.

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.3
• /
• pp.170-175
• /
• 2001

Q-learning is a kind of reinforcement learning where the agent solves the given task based on rewards received from the environment. Most research done in the field of Q-learning has focused on discrete domains, although the environment with which the agent must interact is generally continuous. Thus we need to devise some methods that enable Q-learning to be applicable to the continuous problem domain. In this paper, an extended fuzzy rule is proposed so that it can incorporate Q-learning. The interpolation technique, which is widely used in memory-based learning, is adopted to represent the appropriate Q value for current state and action pair in each extended fuzzy rule. The resulting structure based on the fuzzy inference system has the capability of solving the continuous state about the environment. The effectiveness of the proposed structure is shown through simulation on the cart-pole system.

• Journal of Digital Convergence
• /
• v.4 no.2
• /
• pp.143-151
• /
• 2006

The purpose of this paper is to make a design and implementation of a diagnosis system of learning misconception of students who learn 'be' verb in the English language by using fuzzy theory. In this system, a fuzzy cognitive map exposes the fact that students' perception and misunderstanding about 'the English' language have an intertwined relationship, and diagnoses causes of misconceptions of students by using fuzzy memory associative memory. It suggests that since most existing systems of rule based expert system have had several limitations, this system will be applied to diagnose learners' misconception of learning in varieties of education areas.

• 한국디지털정책학회:학술대회논문집
• /
• 2006.06a
• /
• pp.451-459
• /
• 2006

The purpose of this paper is to make a design and implementation of a diagnosis system of learning misconception of students who learn 'be' verb in the English language by using fuzzy theory. In this system, a fuzzy cognitive map exposes the fact that students' perception and misunderstanding about 'the English' language have an intertwined relationship, and diagnoses causes of misconceptions of students by using fuzzy memory associative memory. It suggests that since most existing systems of rule based expert system have had several limitations, this system will be applied to diagnose learners' misconception of learning in varieties of education areas.

• Earthquakes and Structures
• /
• v.25 no.1
• /
• pp.15-26
• /
• 2023

It is of great importance to assess the residual displacement demand in the performance-based seismic design. In this paper, a hybrid deep learning model for predicting the residual displacement spectra under near-fault (NF) ground motions is proposed by combining the long short-term memory network (LSTM) and back-propagation (BP) network. The model is featured by its capacity of predicting the residual displacement spectrum under a given NF ground motion while considering the effects of structural parameters. To construct this model, 315 natural and artificial NF ground motions were employed to compute the residual displacement spectra through elastoplastic time history analysis considering different structural parameters. Based on the resulted dataset with a total of 9,450 samples, the proposed model was finally trained and tested. The results show that the proposed model has a satisfactory accuracy as well as a high efficiency in predicting residual displacement spectra under given NF ground motions while considering the impacts of structural parameters.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.373-373
• /
• 2021

Rainfall forecasting is an important issue that is applied in many areas, such as agriculture, flood warning, and water resources management. In this context, this study proposed a statistical and machine learning-based forecasting model for monthly rainfall. The Bayesian Gaussian process was chosen to optimize the hyperparameters of the Stacked Long Short-term memory (SLSTM) model. The proposed SLSTM model was applied for predicting monthly precipitation of Seoul station, South Korea. Data were retrieved from the Korea Meteorological Administration (KMA) in the period between 1960 and 2019. Four schemes were examined in this study: (i) prediction with only rainfall; (ii) with deseasonalized rainfall; (iii) with rainfall and minimum temperature; (iv) with deseasonalized rainfall and minimum temperature. The error of predicted rainfall based on the root mean squared error (RMSE), 16-17 mm, is relatively small compared with the average monthly rainfall at Seoul station is 117mm. The results showed scheme (iv) gives the best prediction result. Therefore, this approach is more straightforward than the hydrological and hydraulic models, which request much more input data. The result indicated that a deep learning network could be applied successfully in the hydrology field. Overall, the proposed method is promising, given a good solution for rainfall prediction.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.438-449
• /
• 2022

This study proposes a dependency grammar-based self-attention multilayered bidirectional long short-term memory (DG-M-Bi-LSTM) model for subject-predicate-object (SPO) tuple recognition from natural language (NL) sentences. To add recent knowledge to the knowledge base autonomously, it is essential to extract knowledge from numerous NL data. Therefore, this study proposes a high-accuracy SPO tuple recognition model that requires a small amount of learning data to extract knowledge from NL sentences. The accuracy of SPO tuple recognition using DG-M-Bi-LSTM is compared with that using NL-based self-attention multilayered bidirectional LSTM, DG-based bidirectional encoder representations from transformers (BERT), and NL-based BERT to evaluate its effectiveness. The DG-M-Bi-LSTM model achieves the best results in terms of recognition accuracy for extracting SPO tuples from NL sentences even if it has fewer deep neural network (DNN) parameters than BERT. In particular, its accuracy is better than that of BERT when the learning data are limited. Additionally, its pretrained DNN parameters can be applied to other domains because it learns the structural relations in NL sentences.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.120-126
• /
• 2019

Recently, accurate prediction of power consumption based on machine learning techniques in Internet of Energy (IoE) has been actively studied using the large amount of electricity data acquired from advanced metering infrastructure (AMI). In this paper, we propose a deep learning model based on Gated Recurrent Unit (GRU) as an artificial intelligence (AI) network that can effectively perform pattern recognition of time series data such as the power consumption, and analyze performance of the prediction based on real household power usage data. In the performance analysis, performance comparison between the proposed GRU-based learning model and the conventional learning model of Long Short Term Memory (LSTM) is described. In the simulation results, mean squared error (MSE), mean absolute error (MAE), forecast skill score, normalized root mean square error (RMSE), and normalized mean bias error (NMBE) are used as performance evaluation indexes, and we confirm that the performance of the prediction of the proposed GRU-based learning model is greatly improved.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.249-251
• /
• 2021

In this paper, we introduce the deep-learning system using Tensorflow for recognizing situations that can occur fall situations when the elderly are moving or standing. Fall detection uses the LSTM (long short-term memory) learned using Tensorflow to determine whether it is a fall or not by data measured from wearable accelerator sensor. Learning is carried out for each of the 7 behavioral patterns consisting of 4 types of activity of daily living (ADL) and 3 types of fall. The learning was conducted using the 3-axis acceleration sensor data. As a result of the test, it was found to be compliant except for the GDSVM(Gravity Differential SVM), and it is expected that better results can be expected if the data is mixed and learned.