• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1468-1473
• /
• 2005

In this paper, I proposed the INTelligent Agent System by Kohonen's Self Organizing Neural Network (INTAS). INTAS creates each user's profile from the information. Based on it, learning community grouping suitable to each individual is automatically executed by using unsupervised learning algorithm. In INTAS, grouping and learning are automatically performed on real time by multiagents, regardless of the number of learners. A new framework has been proposed to generate multiagents, and it is a feature that efficient multiagents can be executed by proposing a new negotiation mode between multiagents..

• 전기전자학회논문지
• /
• 제2권1호
• /
• pp.24-33
• /
• 1998

Independent Component analysis (ICA) is a new statistical method for extracting statistically independent components from their linear instantaneous mixtures which are generated by an unknown linear generative model. The recognition model is learned in unsupervised manner so that the recovered signals by the recognition model become the possibly scaled estimates of original source signals. This paper addresses the neural learning approach to ICA. As recognition models a linear feedforward network and a linear feedback network are considered. Associated learning algorithms for both networks are derived from maximum likelihood and information-theoretic approaches, using natural Riemannian gradient [1]. Theoretical results are confirmed by extensive computer simulations.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1017-1021
• /
• 1991

This paper is to explore the potential use of the modeling capacity of neural networks for control applications. The tasks are carried out by two neural networks which act as a plant identifier and a system controller, respectively. Using information stored in the identification network control action has been developed. Without supervising control signals are generated by a gradient type iterative algorithm.

• 감성과학
• /
• 제20권2호
• /
• pp.161-170
• /
• 2017

감정은 학습능력, 행동, 판단력 등 삶의 많은 부분에 영향을 끼치므로 인간의 본질을 이해하는 데 중요한 역할을 한다. 그러나 감정은 개인이 느끼는 강도가 다르며, 시각 영상 자극을 통해 감정을 유도하는 경우 감정이 지속적으로 유지되지 않는다. 이러한 문제점을 극복하기 위하여 총 4가지 감정자극(행복, 슬픔, 공포, 보통) 시 생체신호(뇌전도, 맥파, 피부전도도, 피부 온도)를 획득하고, 이로부터 특징을 추출하여 분류기의 입력으로 사용하였다. 감정 패턴을 확률적으로 해석하여 다른 공간으로 매핑시켜주는 역할을 하는 Restricted Boltzmann Machine (RBM)과 Multilayer Neural Network (MNN)의 은닉층 노드를 이용하여 비선형적인 성질의 감정을 구별하는 Deep Belief Network (DBN) 감정 패턴 분류기를 설계하였다. 그 결과, DBN의 정확도(약 94%)는 오류 역전파 알고리즘의 정확도(약 40%)보다 높은 정확도를 가지며 감정 패턴 분류기로서 우수성을 가짐을 확인하였다. 이는 향후 인지과학 및 HCI 분야 등에서 활용 가능할 것으로 사료된다.

• 한국정밀공학회지
• /
• 제16권11호
• /
• pp.9-15
• /
• 1999

A piezoelectric actuator is widely used in precision positioning applications due to its excellent positioning resolution. However, the piezoelectric actuator lacks in repeatability because of its inherently high hysteresis characteristic between voltage and displacement. In this paper, a controller is proposed to compensate the hysteresis nonlinearity. The controller is composed of a PID and a neural network part in parallel manner. The output of the PID controller is used to teach the neural network controller by the unsupervised learning method. In addition, the PID controller stabilizes the piezoelectric actuator in the beginning of the learning process, when the neural network controller is not learned. However, after the learning process the piezoelectric actuator is mainly controlled by the neural netwok controller. In this paper, the excellent tracking performance of the proposed controller was verified by experiments and was compared with the classical PID controller.

• 한국정밀공학회지
• /
• 제12권12호
• /
• pp.120-129
• /
• 1995

This study introduces a tool wear monitoring technology in face milling operation comprised of an unsupervised neural network. The monitoring system employs two types of sensor signal such as cutting force and acceleration in sensory detection state. The RMS value and band frequency energy of the sensor signals are calculated for te input patterns of neural network. ART2 neural network, which is capable of self organizing without supervised learning, is used for clustering of tool wear states. The experimental results show that tool wear can be effectively detected under various cutting conditions without prior knowledge of cutting processes.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.798-801
• /
• 2002

This paper proposes unsupervised classification of multiple attributes via five-layer autoassociative neural network with bottleneck layer. In the conventional methods, high dimensional data are compressed into low dimensional data at bottleneck layer and then feature extraction is performed (Fig.1). In contrast, in the proposed method, analog data is compressed into digital data. Furthermore bottleneck layer is divided into two segments so that each attribute, which is a discrete value, is extracted in corresponding segment (Fig.2).

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.127.1-127
• /
• 2001

In this paper we propose an input/output model based fault diagnosis method to detect and isolate single faults in the robot arm control system. The proposed algorithm is functionally composed of three main parts-parameter estimation, fault detection, and isolation, When a change in the system occurs, the errors between the system output and the estimated output cross a predetermined threshold, and once a fault in the system is detected, and in this zone the estimated parameters are transferred to the fault classifier by ART2(adaptive resonance theory 2) neural network for fault isolation. Since ART2 neural network is an unsupervised neural network fault classifier does not require the knowledge of all possible faults to isolate the faults occurred in the system. Simulations are carried out to evaluate the performance of the proposed ...

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 추계종합학술대회
• /
• pp.296-300
• /
• 2002

본 연구에서 는 비지도 학습 방식인 SOFM(Self Organize Feature Maps)과 지도 학습인 다층 신경회로망을 이용하여 패턴 분류를 하는 방식을 제안하였다. SOFM을 이용하여 입력 패턴을 분류하여 얻은 결과를 다층 신경회로망의 초기 연결강도와 목표 값으로 설정한다. 제안한 방식의 유용성을 확인하기 위하여 얼굴 영상에 대하여 시뮬레이션한 결과 우수한 성능을 얻었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2806-2825
• /
• 2018

Unsupervised learning has shown good performance on image, video and audio classification tasks, and much progress has been made so far. It studies how systems can learn to represent particular input patterns in a way that reflects the statistical structure of the overall collection of input patterns. Many promising deep learning systems are commonly trained by the greedy layerwise unsupervised learning manner. The performance of these deep learning architectures benefits from the unsupervised learning ability to disentangling the abstractions and picking out the useful features. However, the existing unsupervised learning algorithms are often difficult to train partly because of the requirement of extensive hyperparameters. The tuning of these hyperparameters is a laborious task that requires expert knowledge, rules of thumb or extensive search. In this paper, we propose a simple and effective unsupervised feature learning algorithm for image classification, which exploits an explicit optimizing way for population and lifetime sparsity. Firstly, a sparse target matrix is built by the competitive rules. Then, the sparse features are optimized by means of minimizing the Euclidean norm ($L_2$) error between the sparse target and the competitive layer outputs. Finally, a classifier is trained using the obtained sparse features. Experimental results show that the proposed method achieves good performance for image classification, and provides discriminative features that generalize well.