• 한국지능시스템학회논문지
• /
• 제14권2호
• /
• pp.216-221
• /
• 2004

This paper describes an optimal synthesis method of binary neural network for pattern recognition. Our objective is to minimize the number of connections and the number of neurons in hidden layer by using a Newly Expanded and Truncated Learning Algorithm (NETLA) for the multilayered neural networks. The synthesis method in NETLA uses the Expanded Sum of Product (ESP) of the boolean expressions and is based on the multilayer perceptron. It has an ability to optimize a given binary neural network in the binary space without any iterative learning as the conventional Error Back Propagation (EBP) algorithm. Furthermore, NETLA can reduce the number of the required neurons in hidden layer and the number of connections. Therefore, this learning algorithm can speed up training for the pattern recognition problems. The superiority of NETLA to other learning algorithms is demonstrated by an practical application to the approximation problem of a circular region.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1231-1238
• /
• 1999

This paper presents an approach for the optimal heating load Identification using Diagonal Recurrent Neural Networks(DRNN). In this paper, the DRNN captures the dynamic nature of a system and since it is not fully connected, training is much faster than a fully connected recurrent neural network. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer. The hidden layer is comprised of self-recurrent neurons, each feeding its output only into itself. In this study, A dynamic backpropagation (DBP) with delta-bar-delta learning method is used to train an optimal heating load identifier. Delta-bar-delta learning method is an empirical method to adapt the learning rate gradually during the training period in order to improve accuracy in a short time. The simulation results based on experimental data show that the proposed model is superior to the other methods in most cases, in regard of not only learning speed but also identification accuracy.

• 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.

• 한국정밀공학회지
• /
• 제18권1호
• /
• pp.180-186
• /
• 2001

PID control is widely used in industrial areas, but it is not easy to tune PID gains for an optimal control. The proposed learning method is to tune PID gains using the gradient approach. We use two estimation functions in this method : one is an error function for tuning of PID gains, and the other is a performance measuring function for a completion of learning. This paper shows that optimal PID controllers can be acquired when this learning method is applied to 10 systems with different natural frequencies and damping ratios.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.24.2-24
• /
• 2001

In this paper, the authors present a row dynamic route planning by Q-learning. The proposed algorithm is executed in a cellular automation based traffic simulator, which is also newly created. In Vehicle Information and Communication System(VICS), which is an active field of Intelligent Transport System(ITS), information of traffic congestion is sent to each vehicle at real time. However, a centralized navigation system is not realistic to guide millions of vehicles in a megalopolis. Autonomous distributed systems should be more flexible and scalable, and also have a chance to focus on each vehicles demand. In such systems, each vehicle can search an own optimal route. We employ Q-learning of the reinforcement learning method to search an optimal or sub-optimal route, in which route drivers can avoid traffic congestions. We find some applications of the reinforcement learning in the "static" environment, but there are ...

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5765-5781
• /
• 2018

Extreme learning machine (ELM) is emerging as a powerful machine learning method in a variety of application scenarios due to its promising advantages of high accuracy, fast learning speed and easy of implementation. However, how to select the optimal hidden layer of ELM is still an open question in the ELM community. Basically, the number of hidden layer nodes is a sensitive hyperparameter that significantly affects the performance of ELM. To address this challenging problem, we propose to adopt multiple kernel learning (MKL) to design a multi-hidden-layer-kernel ELM (MHLK-ELM). Specifically, we first integrate kernel functions with random feature mapping of ELM to design a hidden-layer-kernel ELM (HLK-ELM), which serves as the base of MHLK-ELM. Then, we utilize the MKL method to propose two versions of MHLK-ELMs, called sparse and non-sparse MHLK-ELMs. Both two types of MHLK-ELMs can effectively find out the optimal linear combination of multiple HLK-ELMs for different classification and regression problems. Experimental results on seven data sets, among which three data sets are relevant to classification and four ones are relevant to regression, demonstrate that the proposed MHLK-ELM achieves superior performance compared with conventional ELM and basic HLK-ELM.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• 실천공학교육논문지
• /
• 제15권2호
• /
• pp.419-427
• /
• 2023

In this study, optimal adhesion conditions to alleviate defects caused by heat shrinkage with FDM type 3D printers with machine learning are researched. Machine learning is one of the "statistical methods of extracting the law from data" and can be classified as supervised learning, unsupervised learning and reinforcement learning. Among them, a function model for adhesion between the bed and the output is presented using supervised learning specialized for optimization, which can be expected to reduce output defects with FDM type 3D printers by deriving conditions for optimum adhesion between the bed and the output. Machine learning codes prepared using Python generate a function model that predicts the effect of operating variables on adhesion using data obtained through adhesion testing. The adhesion prediction data and verification data have been shown to be very consistent, and the potential of this method is explained by conclusions.

• 한국지능시스템학회논문지
• /
• 제23권4호
• /
• pp.348-353
• /
• 2013

최근들어, 확률론적 최적제어를 포함한 제어이론과 각종 기계학습 기반 인공지능 방법론은 금융공학 분야의 주요 도구로 자리를 잡아 가고 있다. 본 논문에서는 평균회귀 현상을 보이는 시장을 위한 페어 트레이딩 전략 분야와 추세 추종형 트레이딩 전략 분야에 대해 확률론적 최적제어 이론을 활용한 최신 논문 몇 편을 간단히 살펴보고, 보다 융통성 있고 접근성이 좋은 도구를 확보하기 위하여 확률론적 최적제어이론과 기계학습 기법을 동시에 응용하는 전략을 고려한다. 예시를 위하여 실시한 시뮬레이션은 본 논문에서 고려한 전략이 실제 금융시장 데이터를 대상으로 적용될 때 고무적인 결과를 제공할 수 있음을 보여준다.

• 한국인터넷방송통신학회논문지
• /
• 제10권4호
• /
• pp.157-162
• /
• 2010

Cart-pole 균형 문제는 유전자 알고리즘, 인공신경망, 강화학습 등을 이용한 제어 전략 분야의 표준 문제이다. 본 논문에서는 cart-pole 균형문제를 해결하기 위해 실시간 강화 학습을 이용한 접근 방법을 제안하였다. 본 논문의 목적은 cart-pole 균형 문제에서 OREL 학습 시스템의 학습 방법을 분석하는데 있다. 실험을 통해, 본 논문에서 제안한 OREL 학습 방법은 Q-학습보다 최적 값 함수에 더 빠르게 접근함을 알 수 있었다.