• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.941-946
• /
• 2005

In this paper an active random noise control using adaptive learning rate neural networks is presented. The adaptive learning rate strategy increases the learning rate by a small constant if the current partial derivative of the objective function with respect to the weight and the exponential average of the previous derivatives have the same sign, otherwise the learning rate is decreased by a proportion of its value. The use of an adaptive learning rate attempts to keep the learning step size as large as possible without leading to oscillation. It is expected that a cost function minimize rapidly and training time is decreased. Numerical simulations and experiments of active random noise control with the transfer function of the error path will be performed, to validate the convergence properties of the adaptive learning rate Neural Networks. Control results show that adaptive learning rate Neural Networks control structure can outperform linear controllers and conventional neural network controller for the active random noise control.

• 말소리와 음성과학
• /
• 제3권3호
• /
• pp.91-98
• /
• 2011

In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV) algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark's scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.220-225
• /
• 2021

Human population growth rate is an important parameter for real-world planning. Common approaches rely upon fixed parameters like human population, mortality rate, fertility rate, which is collected historically to determine the region's population growth rate. Literature does not provide a solution for areas with no historical knowledge. In such areas, machine learning can solve the problem, but a multitude of machine learning algorithm makes it difficult to determine the best approach. Further, the missing feature is a common real-world problem. Thus, it is essential to compare and select the machine learning techniques which provide the best and most robust in the presence of missing features. This study compares 17 machine learning techniques (base learners and ensemble learners) performance in predicting the human population growth rate of the country. Among the 17 machine learning techniques, random forest outperformed all the other techniques both in predictive performance and robustness towards missing features. Thus, the study successfully demonstrates and compares machine learning techniques to predict the human population growth rate in settings where historical data and feature information is not available. Further, the study provides the best machine learning algorithm for performing population growth rate prediction.

• 산업경영시스템학회지
• /
• 제20권43호
• /
• pp.175-195
• /
• 1997

The learning curve has an important effect the growth of corporation. But, in Korea, the study and inference on the learning rate of each industry are unprepared, and so, Korean industires have difficult in productivity and cost. At this point, this study infers the learning rate of the oil industries and investigates the productivity and growth of them. In conclusion, this study presents the direction of the oil industries' development. With the intention of this objects, this study seizes the status which is concerned the total quantity, the operating rate, the plant capacity, the indicators concerning productivity, the investment of R & D and the scales, and then, infers and verifies the relevancy in connection with the learning rate. In the oil industry, the average rate of learning is 65.96% from 1982 to 1994 which the total quantity and the average operation time are used to infer the rate. To observe the low rate within a same period of time, this study takes the consequences that the learning rate is almost indentical with them each year. This steady state is caused by a difference between the employee and the decision maker about the acquirement and assimiliated of technology. When the high-quality technologies posses the environment to applicate in the scene of labor with them, this technology applies to the productivities. As the learning rate increases, the productivity has more effectiveness. The result of analysis about the effectiveness of the learning rate follows that the R & D unfoldes to exist and does not contribute to the growth of the oil industry. To analyze the variables of the growth, such as the learning rate, the investement of R & D, the operating rate and the gross value added to property, plant and equipment, the model is established and examined. The business strategy in the oil industry must be developed to achive the internal growth as well as the external.

• 한국지능시스템학회논문지
• /
• 제6권2호
• /
• pp.52-56
• /
• 1996

신경망을 학습하는데 있어서, 망의 학습속도는 학습율에 의해 크게 좌우된다. 그러나 대부분의 정적인 학습율 선택 방법들은 몇몇 결정적인 방법들을 제외하곤 경험적인 방식에 의존해 왔다. 경험적인 방식을 사용하여 좋은 학습율을 찾아내는 것은 배우 지류하고 어려운 일이다. 또한 결정적인 방법들은 학습율의 질을 보장하지는 못한다. 본 논문에서 우리는 새로운 학습율 선택 방법을 제안한다. 우리의 방법은 진화 프로그래밍기법을 사용하여 통계적인 방식으로 접근함으로써 좋은 학습율을 찾을 수 있다. 모의 실험을 통하여 우리의 방식이 경험적인 방식들이나 결정적인 방식보다 우수함을 보였다.

• Journal of information and communication convergence engineering
• /
• 제1권3호
• /
• pp.157-162
• /
• 2003

We propose a learning method for improving the performance of the backpropagation algorithm. The proposed method is using a fuzzy logic system for automatic tuning of the learning rate of each weight. Instead of choosing a fixed learning rate, the fuzzy logic system is used to dynamically adjust the learning rate. The inputs of fuzzy logic system are delta and delta bar, and the output of fuzzy logic system is the learning rate. In order to verify the effectiveness of the proposed method, we performed simulations on the XOR problem, character classification, and function approximation. The results show that the proposed method considerably improves the performance compared to the general backpropagation, the backpropagation with momentum, and the Jacobs'delta-bar-delta algorithm.

• 지능정보연구
• /
• 제25권4호
• /
• pp.53-65
• /
• 2019

영상 기반의 보안 시스템의 증가함에 따라 각 용도마다 다른 다양한 객체들에 대한 처리들이 중요해지고 있다. 객체 추적은 객체 인식, 검출과 같은 작업들과 함께 필수적인 작업으로 다뤄진다. 이 객체 추적을 달성하기 위해서 다양한 머신러닝이 적용될 수 있다. 성공적인 분류기로써 전체 에러율 최소화(total-error-rate minimization) 기반의 방법론이 사용될 수 있다. 이 전체 에러율 최소화 기반의 방법론은 오프라인 학습을 기반으로 하고 있다. 객체 추적은 실시간으로 처리하며 갱신해야하는 것이 필수적이므로 온라인 학습(online learning)을 기반으로 하는 것이 적합하다. 온라인 전체 에러율 최소화 방법론이 개발되었지만 점근적으로 재가중되는(approximately reweighted) 작업이 포함되어 에러를 누적시킬 수 있다는 단점이 있다. 본 논문에서는 정확하게 재가중되는(exactly reweighted) 방법론을 제안하면서 온라인 전체 에러율 최소화가 달성되었다. 이 제안된 온라인 학습 방법론을 객체 추적에 적용하여 총 8개의 데이터베이스에서 다른 추적 방법론들 보다 좋은 성능이 달성되었다.

• 무역학회지
• /
• 제46권6호
• /
• pp.191-209
• /
• 2021

In this paper, various time series analysis models and machine learning models are presented for long-term prediction of export growth rate, and the prediction performance is compared and reviewed by RMSE and MAE. Export growth rate is one of the major economic indicators to evaluate the economic status. And It is also used to predict economic forecast. The export growth rate may have a negative (-) value as well as a positive (+) value. Therefore, Instead of using the ReLU function, which is often used for time series prediction of deep learning models, the PReLU function, which can have a negative (-) value as an output value, was used as the activation function of deep learning models. The time series prediction performance of each model for three types of data was compared and reviewed. The forecast data of long-term prediction of export growth rate was deduced by three forecast methods such as a fixed forecast method, a recursive forecast method and a rolling forecast method. As a result of the forecast, the traditional time series analysis model, ARDL, showed excellent performance, but as the time period of learning data increases, the performance of machine learning models including LSTM was relatively improved.

• 전자공학회논문지CI
• /
• 제39권4호
• /
• pp.19-27
• /
• 2002

역전파 알고리즘의 성능 개선을 위해서 학습율을 자동 조정하는 방식을 제안하였다. 제안한 방식은 각각의 연결강도의 학습율을 퍼지 논리 시스템을 이용하여 자동 조정하는 방식으로 각각의 연결강도에 대해서 ${\Delta}$와 $\bar{{\Delta}}$를 구하여 퍼지 논리 시스템의 입력으로 사용하고, 학습율을 출력으로 사용하였다. 제안한 방식을 N-패리티 문제, 함수 근사, 숫자 패턴 분류에 대한 시뮬레이션 결과 일반적인 역전파 알고리즘, 모멘텀 방식, Jacobs의 delta-bar-delta 방식보다 성능이 개선됨을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1239-1242
• /
• 2003

The neural networks are a famous model to learn the nonlinear function or nonlinear system. The main point of neural network is that the difference actual output from desired output is used to update weights. Usually, the gradient descent method is used for the learning process. On training process, if learning rate is too large, neural networks hardly guarantee convergence of neural networks. On the other hand, if learning rate is too small, the training spends much time. Therefore, one major problem in use of neural networks are to decrease the teaming time while neural networks are guaranteed convergence. In this paper, we suggest the model of fuzzy logic to neural networks to calibrate learning rate. This method is to tune learning rate dynamically according to error and demonstrates the optimization of training.