• 정보처리학회논문지B
• /
• 제13B권6호
• /
• pp.615-624
• /
• 2006

이 논문은 이동 에이전트 시스템에 기반을 둔 가상의 병렬분산 컴퓨팅 환경에서 병렬로 수행되는 다층 인공신경망 시뮬레이터를 구현하는 것을 목적으로 한다. 다층 신경망은 학습세션, 학습데이터, 계층, 노드, 가중치 수준에서 병렬화가 이루어진다. 이 논문에서는 네트워크의 통신량이 상대적으로 적은 학습세션 및 학습데이터 수준의 병렬화가 가능한 신경망 시뮬레이터를 개발하고 평가하였다. 평가결과, 학습세션 병렬화와 학습데이터 병렬화 성능분석에서 약 3.3배의 학습 수행 성능 향상을 확인할 수 있었다. 가상의 병렬 컴퓨터에서 신경망을 병렬로 구현하여 기존의 전용병렬컴퓨터에서 수행한 신경망의 병렬처리와 비슷한 성능을 발휘한다는 점에서 이 논문의 의의가 크다고 할 수 있다. 따라서 가상의 병렬 컴퓨터를 이용하여 신경망을 개발하는데 있어서, 비교적 시간이 많이 소요되는 학습시간을 줄임으로서 신경망 개발에 상당한 도움을 줄 수 있다고 본다.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.1073-1080
• /
• 1996

The impact of the input and output probability distributions on the performance of neural networks to forecast two year peak stream flow (cubic meters per second) is examined for two major river basins of the US. The neural network input consisted of drainage area(square kilometers ) and elevation (meters). When data are normally distributed , the neural networks predict much better than when the data are non-normal and have larger tails in their distributions.

• Journal of applied mathematics & informatics
• /
• 제29권1_2호
• /
• pp.103-117
• /
• 2011

By using an important lemma, some analysis techniques and Lyapunov functional method, we establish the sufficient conditions of the existence of equilibrium solution of a class of BAM neural network with impulses and distributed delays. Finally, applications and an example are given to illustrate the effectiveness of the main results.

• 대한기계학회논문집A
• /
• 제23권11호
• /
• pp.1929-1939
• /
• 1999

This paper presents a neural network approach, which was named PRONET, to 3D object recognition and pose calculation. 3D objects are represented using a set of centroidal profile patterns that describe the boundary of the 2D views taken from evenly distributed view points. PRONET consists of the training stage and the execution stage. In the training stage, a three-layer feed-forward neural network is trained with the centroidal profile patterns using an error back-propagation method. In the execution stage, by matching a centroidal profile pattern of the given image with the best fitting centroidal profile pattern using the neural network, the identity and approximate orientation of the real object, such as a workpiece in arbitrary pose, are obtained. In the matching procedure, line-to-line correspondence between image features and 3D CAD features are also obtained. An iterative model posing method then calculates the more exact pose of the object based on initial orientation and correspondence.

• Tribology and Lubricants
• /
• 제30권6호
• /
• pp.356-363
• /
• 2014

Marine diesel engines operate in environments in which damage easily occurs from corrosion. Recently, damage to cylinder liners has increased from corrosion wear caused by increased engine power. This damage can cause serious problems in the economy. Thus, many researchers have treated and studied damaged cylinder liners. However, a method is necessary for real-time monitoring of damage to cylinder liners during operation of the engine, before serious damage can occur. This study carries out reciprocating friction and wear tests on a cast iron specimen under various corrosion atmospheres and verifies the variations of friction coefficient and friction surface. Additionally, the friction coefficient and friction status are predicted by using a neural network that learns the vibration and frequency spectrum data from an acceleration sensor. According to our conclusions, amplitude is distributed highly at high frequencies, and values of standard deviation and kurtosis are high when damage to the friction surface is serious. The accuracy rate of the friction coefficient predicted by the neural network is over 80% of the real measured value without NaCl, and application of the neural network is very effective for diagnosing the friction condition and damage to the cylinder liner.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.993-996
• /
• 1993

This paper addresses the structure and its associated learning algorithms of a feedforward multi-layered connectionist network, which has distributed learning abilities, for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed neural-network-based fuzzy logic control system (NN-FLCS) can be contrasted with the traditional fuzzy logic control system in their network structure and learning ability. An on-line supervised structure/parameter learning algorithm dynamic learning algorithm can find proper fuzzy logic rules, membership functions, and the size of output fuzzy partitions simultaneously. Next, a Reinforcement Neural-Network-Based Fuzzy Logic Control System (RNN-FLCS) is proposed which consists of two closely integrated Neural-Network-Based Fuzzy Logic Controllers (NN-FLCS) for solving various reinforcement learning problems in fuzzy logic systems. One NN-FLC functions as a fuzzy predictor and the other as a fuzzy controller. As ociated with the proposed RNN-FLCS is the reinforcement structure/parameter learning algorithm which dynamically determines the proper network size, connections, and parameters of the RNN-FLCS through an external reinforcement signal. Furthermore, learning can proceed even in the period without any external reinforcement feedback.

• International journal of advanced smart convergence
• /
• 제12권2호
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.243-248
• /
• 1996

In this paper, a general neural-network-based connectionist model, called Fuzzy Neural Network(FNN), is proposed for the realization of a fuzzy logic control system. The proposed FNN is a feedforward multi-layered network which integrates the basic elements and functions of a traditional fuzzy logic controller into a connectionist structure which has distributed learning abilities. Such FNN can be constructed from training examples by learning rule, and the connectionist structure can be trained to develop fuzzy logic rules and find optimal input/output membership functions. Computer simulation examples will be presented to illustrate the performance and applicability of the proposed FNN, and their associated learning algorithms.

• 한국지능시스템학회논문지
• /
• 제11권4호
• /
• pp.354-358
• /
• 2001

본 논문에서는 underutilization 문제를 해결한 퍼지 신경회로망 모델을 제시한다. 이 퍼지 신경 회로망은 ART-1 신경회로망과 유사한 제어 구조를 가지고 있어 유연성이 있으면서도 안정성이 있다. 또한 연결강도의 초기화가 필요 없고 ART-1 신경회로망에 비하여 잡음에 민감하지 않다. 이 퍼지 신경회로망의 학습법칙은 코호넨의 학습법칙을 변형하고 퍼지화 하였으며 누설 경쟁학습의 퍼지화와 조건 확률의 퍼지화에 기반을 두고 있다. 출력 뉴런 중에서 승자를 정한 후에 행해지는 점검 테스트에서는 유사척도로 상대적 거리를 사용하였다. 이 상대적 거리는 유클리디안 거리와 함께 데이터와 클러스터들의 대푯값들 간의 상대적인 위치를 고려한 것이다. 본 논문에서 제안한 퍼지 신경회로망과 코호넨 자기 조직화 특징 지도의 성능을 비교하기 위하여 널리 사용되어온 IRIS 데이터와 가우시안 분포 데이터를 사용하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.267-270
• /
• 1997

As an approach to develope a control system with robustness in changing control environment conditions, this paper will propose a robot manipulator control system using multilayer neural network and immune algorithm. The proposed immune algorithm which has the characteristics of immune system such as distributed and anomaly detection, probabilistic detection, learning and memory, consists of the innate immune algorithm and the adaptive immune algorithm. We will demonstrate the effectiveness of the proposed control system with simulations of a 2-link robot manipulator.