• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.52-56
• /
• 1996

In trainir~ga back-propagation neural network, the learning speed of the network is greatly affected by its learning rate. Most of off-line fashioned learning-rate selection methods, however, are empirical except for some deterministic methods. It is very tedious and difficult to find a good learning rate using the empirical methods. The deterministic methods cannot guarantee the quality of the quality of the learning rate. This paper proposes a new learning-rate selection method. Our off-line fashioned method selects a good learning rate through stochastically searching process using evolutionary programming. The simulation results show that the learning speed achieved by our method is superior to that of deterministic and empirical methods.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.1
• /
• pp.63-68
• /
• 2017

This paper reviews the learning model of a forward slip ratio in order to improve the mass-flow stability and strip qualities in the hot strip finishing mill process. Firstly, it is shown, from mathematical analysis, that the significant parameters of the forward slip ratio are the tension, looper angle, and roll velocity. Secondly, a discrete-time learning model of the forward slip ratio is proposed from these parameters, which is identified by an instrumental variable (IV) identification algorithm. Finally, it is shown from computer simulation that the proposed learning model is more effective than the existing learning model.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.358-360
• /
• 2005

본 논문은 학습자의 학업 성취도를 높이기 위해 학습자의 수준에 맞는 평가 문항을 제공하기 위한 방안으로 문제의 정${\cdot}$오답율을 측정하고, 코스 구성시 측정된 정${\cdot}$오답율을 근거로 문제를 구성하는 방안을 제안한다. 기존 연구는 학습자의 수준에 맞는 콘텐츠 제작에만 중점을 두었으나 본 연구에서는 수준에 맞는 평가를 제공함으로써 학습자의 학업 성취도를 높일 수 있다. 학습자의 수준은 기존 학습의 결과로 파악이 되며, LMS에 저장된다. 학습자가 문제를 풀면 정${\cdot}$오답 결과를 저장하여 해당 문제를 푼 여러 학습자들의 정${\cdot}$오답율을 메타데이터에 포함한다. 교수자는 학습 코스 설계 시 해당 학습자의 수준에 맞는 평가 문항 검색, 새로운 코스에 포함 할 수 있다. 이를 통해 학습 코스 설계자는 학습자의 수준에 맞는 평가 문항을 학습코스에 적용할 수 있고, 학습자는 자신의 수준에 맞는 평가를 함으로써 학업성취도가 높아지게 된다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.313-315
• /
• 2002

본 논문에서는 학습 중 모멘트를 동적으로 조절하여 수련속도와 학습 성능을 향상시키는 동적모멘트를 제안하고 회귀방법으로 동적모멘트의 성능을 재확인한다. 제안된 학습방법은 기존의 정적모멘트와는 달리 수렴 정도에 따라 현재의 학습에 과거의 학습률을 단리 반영하는 방법으로 다른 학습법에 비해 보다 유연한 초평면을 갖으며 수렴에 이르는 시간이 오래 걸리는 KR(Kernel Relaxation)에 적용하여 그 성능을 확인한다. 본 논문에서 사용한 회귀방법은 RMS 오류율을 사용하였으며 제안된 학습방법인 동적모멘트를 SVM(support vector machine)의 순차 학습방법 중 최근 발표된 KR에 적용하여 RMS 오류율을 확인하였다. 실험의 공정성을 위해 신경망 분류기 표준평가데이터인 SONAR 데이터를 사용하였으며 실험 결과 동적모멘트를 이용한 회귀율이 정적모멘트를 이용한 방법보다 향상되었음을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.6 no.5
• /
• pp.788-796
• /
• 2003

This paper proposes using dynamic momentum for squential learning method. Using The dynamic momentum improves convergence speed and performance by the variable momentum, also can identify it in the RMSE(root mean squared error). The proposed method is reflected using variable momentum according to current state. While static momentum is equally influenced on the whole, dynamic momentum algorithm can control the convergence rate and performance. According to the variable change of momentum by training. Unlike former classification and regression problems, this paper confirms both performance and regression rate of the dynamic momentum. Using RMSE(root mean square error ), which is one of the regression methods. The proposed dynamic momentum has been applied to the kernel adatron and kernel relaxation as the new sequential learning method of support vector machine presented recently. In order to show the efficiency of the proposed algorithm, SONAR data, the neural network classifier standard evaluation data, are used. The simulation result using the dynamic momentum has a better convergence rate, performance and RMSE than those using the static moment, respectively.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.813-824
• /
• 2021

To improve educational performance by analyzing the learning trends of adult learners of Open High Schools, various algorithm models using artificial intelligence were designed and performance was evaluated by applying them to real data. We analyzed Log data of 115 adult learners in the cyber education system of Open High Schools. Most adult learners of Open High Schools learned more than recommended learning time, but at the end of the semester, the actual learning time was significantly reduced compared to the recommended learning time. In the second half of learning, the participation rate of VODs, formation assessments, and learning activities also decreased. Therefore, in order to improve educational performance, learning time should be supported to continue in the second half. In the latter half, we developed an artificial intelligence algorithm models using Tensorflow to predict learning time by data they started taking the course. As a result, when using CNN(Convolutional Neural Network) model to predict single or multiple outputs, the mean-absolute-error is lowest compared to other models.

• Journal of the Korean Society for information Management
• /
• v.19 no.4
• /
• pp.5-34
• /
• 2002

The purpose of this study is to investigate the effects of learning methods on students' information retrieval and information synthesis capability in web. This is an experimental study comparing the two different learning methods as task-based learning and technic-based learning. The findings of this study were as follows: 1. The task-based learning was more effective than the technic-based learning in information achievements as information retrieval capability (t= 3.59, p〈.05). 2. In the 1st retrieval (recall ratio t=1.81 precision ratio t=.61) of Naver Korean Web Retrieval, there was no significant difference (p〉.05). In the 2nd retrieval (recall ratio t=2.93 precision ratio t=2.45) and 3rd retrieval (recall ratio t=3.48 precision ratio t= 2.50), the task-based group was more effective than the technic-based group (p〈.05). 3. There was no significant difference in students' information synthesis capability between the task-based learning and technic-based learning (t= 1.95, p〉.05). The findings of this study suggest that the task-based learning approach is more effective to improve students' information literacy, and that professionals should consider better instructional principles for the improvement of instructional quality.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.4
• /
• pp.19-27
• /
• 2002

We proposed an auto-tuning method of learning rate for performance improvement of backpropagation algorithm. Proposed method is used a fuzzy logic system for automatic tuning of learning rate. Instead of choosing a fixed learning rate, the fuzzy logic system is used to dynamically adjust learning rate. The inputs of fuzzy logic system are ${\Delta}$ and $\bar{{\Delta}}$, and the output is the learning rate. In order to verify the effectiveness of the proposed method, we performed simulations on a N-parity problem, function approximation, and Arabic numerals classification. The results show that the proposed method has considerably improved the performance compared to the backpropagation, the backpropagation with momentum, and the Jacobs' delta-bar-delta.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1285-1288
• /
• 2015

본 논문에서는 영상인식을 위한 딥 러닝에서 사용되는 매개변수 최적화 방법을 제안한다. 학습 성능에 영향을 미치는 매개변수 중 이미지 배치 사이즈 값, 초기 학습율, 최대 학습 반복 횟수에 대해 상호간의 관계를 분석하고 성능을 개선시키기 위해 값을 최적화하는 방법을 연구한다. 제안된 방법을 통한 개선 정도를 분석하기 위해 매개변수의 변화에 따른 학습 소요 시간, 정확도 향상 추이, 메모리 사용량의 변화를 측정한다. 측정된 학습 소요 시간, 정확도 향상 추이, 메모리 사용량의 변화를 분석한 결과 배치 사이즈와 초기 학습 율은 같은 비율로 반비례하게 값을 적용할 때가 이상적 이였으며 서로 다른 환경에서 각각의 학습 소요시간을 측정하는 것으로 배치 사이즈 값과 초기 학습 율에 따른 최적의 최대 학습 반복 횟수를 획득할 수 있었다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.8
• /
• pp.66-74
• /
• 2014

Recently a variety of study of Korean parsing system is carried out by many software engineers and linguists. The parsing system mainly uses the method of machine learning or symbol processing paradigm. But the parsing system using machine learning has long training time because the data of Korean sentence is very big. And the system shows the limited recognition rate because the data has self error. In this thesis we design system using feature module which can reduce training time and analyze the recognized rate each the number of training sentences and repetition times. The designed system uses the separated modules and sorted table for binary search. We use the refined 36,090 sentences which is extracted by Sejong Corpus. The training time is decreased about three hours and the comparison of recognized rate is the highest as 84.54% when 10,000 sentences is trained 50 times. When all training sentence(32,481) is trained 10 times, the recognition rate is 82.99%. As a result it is more efficient that the system is used the refined data and is repeated the training until it became the steady state.