• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.4
• /
• pp.39-48
• /
• 1996

비선형 동적 시스템을 제어하기에 적합한 귀환 신경망에 대한 연구는 안정성(stability) 유도와 학습 알고리듬(learning algorithm) 개발의 두가지 방향으로 지금까지 많은 연구가 이루어져 왔다. 본 논문에서는 비선형 동적 시스템 제어시 온라인(on-line) 학습이 가능하고 안정성을 보장하도록 귀환 신경망의 학습 알고리듬에 VSS이론을 도입하여 개발한다. 또한 개발한 학습 알고리듬을 사용한 귀환 신경망을 전형적인 비선형 동적 시스템인 로보트 매니퓰레이터의 제어 시스템에 적용하고 기존의 학습 방법의 적용 결과와 비교하여 개발한 제어 알고리듬의 효용성을 입증한다.

• Journal of the Korean Society of Radiology
• /
• v.10 no.8
• /
• pp.637-643
• /
• 2016

Due to the popularity of artificial intelligent, medical image processing using artificial neural network is increasingly attracting the attention of academic and industry researches. Deep learning with a convolutional neural network has been proved to very effective representation of images. However, the training process requires high performance H/W platform. Thus, the realtime learning of a large number of high dimensional samples within low-power devices is a challenging problem. In this paper, we attempt to establish this possibility by presenting a realtime neural network method on Raspberry pi using online sequential extreme learning machine. Our experiments on high-dimensional dataset show that the proposed method records an almost real-time execution.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.2 s.95
• /
• pp.211-217
• /
• 1999

감지기의 고장 발견, 확인, 보완은 복잡한 항공 시스템의 중요한 문제로 부각되어 왔으며, 그동안 칼만 필터를 이용한 기존 추정기술 혹은 온라인 학습 인공지능 알고리듬 등이 이 같은 문제를 해결하기 위해 제시되어 왔다. 본 연구에서는 여분의 감지기가 없는 항공제어계에 대해 온라인 학습 신경망을 이용한 감지기의 고장 발견, 확인, 그리고 보완에 관해 초점을 둔다. 이 내고장성 항공제어계는 주 신경조직망과 n개의 국소 신경조직망으로 이루어지는데, 포괄적인 감지기의 고장을 발견하는 능력을 가진다. 어떤 경우에서는 기존의 감지기 고장 발견 방법의 성능을 향상시키기 위해 수정된 감지방법이 소개되고 그 보완된 감지방법을 이용하여 기존의 방법과 성능비교가 이루어졌다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.11-12
• /
• 2017

본 논문에서는 부류가 정해진 훈련 집합이 불필요한 온라인 학습 기반 추적 기법을 제안한다. 추적기의 학습을 위해 합성곱 신경망(convolutional neural network: CNN)을 이용하였다. 추적영상으로부터 직접 훈련 샘플을 수집함으로써 분류기 학습을 위한 비용을 감소시킬 수 있었고, 목표 영상에 적응적인 객체 모델을 생성할 수 있다. 실험 결과를 통해 제안하는 방법이 우수한 성능을 보임을 입증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.330-331
• /
• 2017

최근 클라우드 및 신경망 기반의 지능형 CCTV기술이 사회 안전 분야의 핵심 기술로 부상하면서 신학계에 관심이 커지고 있다. 이러한 동향을 반영하여 공공/사회 안전을 위한 실 환경 기반 지능형 영상 인식 기술의 지속적인 성능 업데이트 및 관리를 위한 온라인 학습 기반 인식 기술이 필요하다. 본 논문에서는 클라우드 기반 지능형 영상보안 온라인 인큐베이팅 플랫폼 기술 과제를 소개한다. 온라인 인식신경망 인큐베이팅이란, 원격 클라우드 환경을 이용하여 사용 중인 영상인식 신경망을 온라인 학습으로 실시간 업데이트하여 딥러닝 성능을 지속적으로 강화하는 기술이다. 본 논문에서는 클라우드 기반 지능형 영상보안 인큐베이팅 플랫폼 기술 과제를 소개한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.602-608
• /
• 2011

In this study, a method of designing a neurointerface using neural network (NN) is proposed for controlling nonholonomic mobile robots. According to the concept of virtual master-slave robots, in particular, a partially stable inverse dynamic model of the master robot is acquired online through the NN by applying a feedback-error learning method, in which the feedback controller is assumed to be based on a PD compensator for such a nonholonomic robot. The NN for the online feedback-error learning can composed that the input layer consists of six units for the inputs $x_i$, i=1~6, the hidden layer consists of two hidden units for hidden outputs $o_j$, j=1~2, and the output layer consists of two units for the outputs ${\tau}_k$, k=1~2. A tracking control problem is demonstrated by some simulations for a nonholonomic mobile robot with two-independent driving wheels. The initial q value was set to [0, 5, ${\pi}$].

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.614-618
• /
• 2016

As information on the internet and the data from smart devices are growing, the amount of stream data is also increasing in the real world. The stream data, which is a potentially large data, requires online learnable models and algorithms. In this paper, we propose a novel class of models: predictive convolutional neural networks to be able to perform online learning. These models are designed to deal with longer patterns as the layers become higher due to layering convolutional operations: detection and max-pooling on the time axis. As a preliminary check of the concept, we chose two-month gathered GPS data sequence as an observation sequence. On learning them with the proposed method, we compared the original sequence and the regenerated sequence from the abstract information of the models. The result shows that the models can encode long-range patterns, and can generate a raw observation sequence within a low error.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.3
• /
• pp.72-83
• /
• 2000

This paper presents the implementation of the position control system for 3 phase induction motor using reaching mode controller and neural networks. The reaching mode controller is used to bring the position error and speed error trajectories toward the sliding surface and to train neural networks at the first time. The structure of the reaching mode controller consists of the switch function of sliding surface. And feedforward neural networks approximates the equivalent control input using the reference speed and reference position and actual speed and actual position measured form an encoder and, are tuned on-line. The reaching mode controller and neural networks are applied to the position control system for 3 phase induction motor and, are compared with a PI controller through computer simulation and experiment respectively. The results are illustrated that the output of reaching mode controller is decreased and feedforward neural networks take charge of the main part for the control action, and the proposed controllers show better performance than the PI controller in abrupt load variation and the precise control is possible because the steady state error can be minimized by training neural networks.

• The KIPS Transactions:PartB
• /
• v.11B no.7 s.96
• /
• pp.831-840
• /
• 2004

In this paper, we propose a scheme to implement intelligent game characters based on neural networks. Neural networks that implement in-telligent game character receive the action of an opponent character and the distance between them, decide intelligent character's action, and output the decision. The neural networks are trained by reinforcement learning using the scores acquired by the actions of two characters as reinforcement values. To show the usefulness of the proposed scheme, a simple fighting action game is implemented and various experiments are performed. Experimental results show that proposed intelligent characters can learn the rule of the game. The proposed scheme can be ap-plied to massively multiple online games as well as fighting action games.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.5
• /
• pp.430-437
• /
• 2002

Having a variety of good characteristics against other pattern recognition techniques, the multilayer perceptron (MLP) has been widely used in speech recognition and speaker recognition. But, it is known that the error backpropagation (EBP) algorithm that MLP uses in learning has the defect that requires restricts long learning time, and it restricts severely the applications like speaker recognition and speaker adaptation requiring real time processing. Because the learning data for pattern recognition contain high redundancy, in order to increase the learning speed it is very effective to use the online-based learning methods, which update the weight vector of the MLP by the pattern. A typical online EBP algorithm applies the fixed learning rate for each update of the weight vector. Though a large amount of speedup with the online EBP can be obtained by choosing the appropriate fixed rate, firing the rate leads to the problem that the algorithm cannot respond effectively to different learning phases as the phases change and the number of patterns contributing to learning decreases. To solve this problem, this paper proposes a Changing rate and Omitting patterns in Instant Learning (COIL) method to apply the variable rate and the only patterns necessary to the learning phase when the phases come to change. In this paper, experimentations are conducted for speaker verification and speech recognition, and results are presented to verify the performance of the COIL.