• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.301-308
• /
• 1997

The learning speed of the neural networks, the most important factor in applying to real problems, greatly depends on the learning rate of the networks, Three approaches-empirical, deterministic, and stochastic ones-have been proposed to date. We proposed a new learning-rate selection algorithm using an evolutionary programming search scheme. Even though the performance of our method showed better than those of the other methods, it was found that taking much time for selecting evolutionary learning rates made the performance of our method degrade. This was caused by using static intervals (called static windows) in order to update learning rates. Out algorithm with static windows updated the learning rates showed good performance or didn't update the learning rates even though previously updated learning rates shoved bad performance. This paper introduce a window control scheme to avoid such problems. With the window control scheme, our algorithm try to update the learning ra es only when the learning performance is continuously bad during a specified interval. If previously selected learning rates show good performance, new algorithm will not update the learning rates. This diminish the updating time of learning rates greatly. As a result, our algorithm with the window control scheme show better performance than that with static windows. In this paper, we will describe the previous and new algorithm and experimental results.

• 한국컴퓨터정보학회논문지
• /
• 제25권7호
• /
• pp.39-46
• /
• 2020

최근, 대전 게임 분야에서, 가상 캐릭터들의 효과적인 설계를 위해 캐릭터의 승률을 효율적으로 예측할 수 있는 방법들이 매우 필요하다. 우리는 본 논문에서 이 문제를 해결하기 위해 시뮬레이션과 기계 학습을 결합하는 방법을 제안한다. 우선 대전 게임에서 가상 캐릭터의 대전 승률을 분석하기 위해서 시뮬레이션을 사용하고, 가상 캐릭터의 능력치에 따라서 승률을 예측하기 위해 회귀 모델에 기반한 기계 학습 기법을 적용한다. 제안한 기법으로 실험한 결과는 시뮬레이션 결과로 나온 승률과 기계 학습 기법이 예측한 승률이 거의 차이가 없다는 것을 확인하였다. 그리고 간단한 회귀 모델에 기반한 기계 학습으로도 실험에서 좋은 성능을 얻을 수 있었다.

• 한국지능시스템학회논문지
• /
• 제15권7호
• /
• pp.800-804
• /
• 2005

본 논문에서는 LVQ(Learning )rector Quantization)을 퍼지화한 새로운 퍼지 학습 법칙을 제안하였다. 퍼지 학습 법칙 3은 기존의 학습률 대신에 퍼지 학습률을 사용하였는데, 기존의 LVQ와는 달리 비대칭인 학습률을 사용하였다. 기존의 LVQ에서는 분류가 맞거나 틀렸을 때 같은 학습률을 사용하고 부호만 달랐으나, 새로운 퍼지 학습 법칙에서는 분류가 맞거나 틀렸을 때 부호가 다를 뿐만 아니라 학습률도 다르다. 이 새로운 퍼지 학습 법칙을 무감독 신경회로망인 improved IAFC (Integrated Adaptive Fuzzy Clustering) 신경회로망에 적용하여 감독 신경회로망으로 변형하였다. Improved IAFC 신경회로망은 유연성이 있으면서도 안정성이 있다. 제안한 supervised IAFC 신경회로망 3의 성능과 오류 역전파 신경회로망의 성능을 비교하기 위하여 iris 데이터를 사용하였는데, supervised IAFC 신경회로망 3가 오류 역전파 신경회로망보다 성능이 우수하였다.

• 전자공학회논문지B
• /
• 제31B권11호
• /
• pp.142-150
• /
• 1994

본 논문은 분류된 학습률을 이용한 고속 경쟁 학습에 대한 연구이다. 이연구의 기본 개념은 각 출력 노우드의 연결강도 벡터에 분류된 학습률을 할당하는 것이다. 출력 노우드의 각 연결강도 벡터는 자기 자신의 학습률에 의하여 갱신된다. 각 학습률은 관련되는 출력 노우드가 경쟁에서 승리할 때에만 변화되며, 승리하지 못한 노우드들의 학습률은 변화되지 않는다. 영상 벡터 양자화에 대하여 실험한 결과는 제안한 방법이 기존 경쟁 학습 방법에 비하여 더 빠르게 학습되고 더 좋은 화질을 갖게 됨을 보였다.

• 한국콘텐츠학회논문지
• /
• 제4권3호
• /
• pp.99-105
• /
• 2004

이 논문은 다층퍼셉트론의 학습을 빠르게 하기 위한 최적 학습률을 제안한다. 이 학습률은 한 뉴런에 연결된 가중치들에 대한 학습률과, 중간층에 가상의 목표값을 설정하기 위한 학습률로 나타난다. 그 결과, 중간층 가중치의 최적 학습률은 가상의 중간층 목표값 할당 성분과 중간층 오차함수를 최소화 시키고자하는 성분의 곱으로 나타난다. 제안한 방법은 고립단어인식과 필기체 숫자 인식 문제의 시뮬레이션으로 효용성을 확인하였다.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1048-1063
• /
• 2020

In this study, we propose a reinforcement learning agent to control the data transmission rates of nodes in carrier sensing multiple access with collision avoidance (CSMA/CA)-based wireless networks. We design a reinforcement learning (RL) agent, based on Q-learning. The agent learns the environment using the timeout events of packets, which are locally available in data sending nodes. The agent selects actions to control the data transmission rates of nodes that adjust the modulation and coding scheme (MCS) levels of the data packets to utilize the available bandwidth in dynamically changing channel conditions effectively. We use the ns3-gym framework to simulate RL and investigate the effects of the parameters of Q-learning on the performance of the RL agent. The simulation results indicate that the proposed RL agent adequately adjusts the MCS levels according to the changes in the network, and achieves a high throughput comparable to those of the existing data transmission rate adaptation schemes such as Minstrel.

• Journal of the Korean Statistical Society
• /
• 제36권3호
• /
• pp.367-372
• /
• 2007

Classification as a tool to extract information from data plays an important role in science and engineering. Among various classification methodologies, support vector machine has recently seen significant developments. The central problem this paper addresses is the accuracy of support vector machine. In particular, we are interested in the situations where fast rates of convergence to the Bayes risk can be achieved by support vector machine. Through learning examples, we illustrate that support vector machine may yield fast rates if the space spanned by an adopted kernel is sufficiently large.

• 충청수학회지
• /
• 제34권2호
• /
• pp.157-168
• /
• 2021

This study uses the benchmark interest rate of the Federal Open Market Committee (FOMC) to predict gold futures prices. For the predictions, we used the support vector machine (SVM) (a machine-learning model) and the long short-term memory (LSTM) deep-learning model. We found that the LSTM method is more accurate than the SVM method. Moreover, we applied the Boruta algorithm to demonstrate that the FOMC benchmark interest rates correlate with gold futures.

• 무역학회지
• /
• 제46권1호
• /
• pp.169-187
• /
• 2021

This paper analyzes the feasibility of using machine learning and deep learning methods to forecast the income and employment using the strategic industries as well as investment, export, and exchange rates. The decision tree, artificial neural network, support vector machine, and deep learning models were used to forecast the income and employment in Busan. The following were the main findings of the comparison of their predictive abilities. First, the decision tree models predict the income and employment well. The forecasting values for the income and employment appeared somewhat differently according to the depth of decision trees and several conditions of strategic industries as well as investment, export, and exchange rates. Second, since the artificial neural network models show that the coefficients are somewhat low and RMSE are somewhat high, these models are not good forecasting the income and employment. Third, the support vector machine models show the high predictive power with the high coefficients of determination and low RMSE. Fourth, the deep neural network models show the higher predictive power with appropriate epochs and batch sizes. Thus, since the machine learning and deep learning models can predict the employment well, we need to adopt the machine learning and deep learning models to forecast the income and employment.

• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.175-182
• /
• 1994

In this study, we present unvoiced consonant recognition system using characteristic parameters of the phoneme of the each syllable. For the recognition, the characteristic parameters on the time domain such as ZCR, total energy of the consonant region and half region energy of the consonant region, and those on the frequency domain such as the frequency spectrum of the transition region are used. The objective unvoiced consonants in this study are /ㄱ/,/ㄷ/,/ㅂ/,/ㅈ/,/ㅋ/,/ㅌ/,/ㅍ/ and /ㅊ/. Each characteristic parameter of two regions extracted from these segmented unvoiced consonants are used for each recognition system of the region, independently, And complementing two outputs of each other system, the final output is to be produced. The recognition system is implemented using MLP which has learning ability. The recognition simulation results for 112 unvoiced consonant samples are that average recognition rates are 96.4$\%$ under 80$\%$ learning rates and 93.7$\%$ under 60$\%$ learning rates.