• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.115.3-115
• /
• 2001

In this paper, discrete-time cellular neural networks are designed in order to function as associative memories by using Hebbian learning rule and non-cloning template. The proposed method has a very simple structure to design and to learn. Weights are updated by the connection between the neuron and its neighborhood. In the simulation, the proposed method is applied to the classification of a traffic sign pattern.

• 한국통신학회논문지
• /
• 제25권4B호
• /
• pp.783-787
• /
• 2000

현재 사용되고 있는 개인용 컴퓨터의 중앙처리장치로서 주종을 이루고 있는 마이크로프로세서는 256KB, 혹은 512KB의 L2(Second Level) 캐쉬를 Direct Mapping, 32B 라인사이즈, 그리고 Write Allocation을 채택하지 않는 형태로 사용하고 있는데, 이러한 L2 캐쉬에서 Mapping 방식을 8-way Set Associative Mapping Procedure로 바꾸고, 라인사이즈를 늘려서 128B 이상으로 변경하고, 그리고 Write Allocation을 채택하였을 경우 그 적중률(Hit Ratio)이 약간의 하드웨어적 추가 비용만으로 2.5% 정도 개선됨을 확인하였다.

• 한국산업정보학회논문지
• /
• 제6권3호
• /
• pp.29-34
• /
• 2001

본 논문에서는 신경회로망을 이용하여 아날로그 시 계열정보를 직접 처리할 수 있는 연상기억 시스템을 제안한다. 제안하는 시스템은 시 계열정보를 상기할 때 현재의 정보와의 일치 결과만으로 출력(상기결과)을 결정하는 것 외에 과거의 일치결과도 고려한 상태에서 출력을 결정하는 시스템이다. 시스템의 기본적인 능력을 조사하기 위하여 기억패턴을 주기계열로 그리고 하중은 전부 고정하는 조건으로 단순화하여 시뮬레이션을 행하여 오류정정 능력을 갖는 것을 확인하였다. 시간축 방향의 하중을 적절하게 설정하면 기억용량의 증대나 상기 오류의 저감 등의 효과가 기대된다.

• 전자공학회논문지B
• /
• 제33B권2호
• /
• pp.118-130
• /
• 1996

Fuzzy inference is very useful in expressing ambiguous problems quantitatively and solving them. But like the most of the knowledge based inference systems. It has many difficulties in constructing rules and no learning capability is available. In this paper, we proposed a fuzzy inference system based on fuzy associative memory to solve such problems. The inference system proposed in this paper is mainly composed of learning phase and inference phase. In the learning phase, the system initializes it's basic structure by determining fuzzy membership functions, and constructs fuzzy rules in the form of weights using learning function of fuzzy associative memory. In the inference phase, the system conducts actual inference using the constructed fuzzy rules. We applied the fuzzy inference system proposed in this paper to a pattern classification problem and show the results in the experiment.

• 대한전자공학회논문지
• /
• 제26권5호
• /
• pp.79-84
• /
• 1989

신경회로의 이차 비선형 연상기억모델을 광학적으로 구현하였다. 이 때 신경소자들 간의 가중 $N^3$연결은 광벡터-행렬 곱셈기와 연결홀로그램으로 실현하였고 구성된 시스템이 연상기억작용을 나타냄을 관측하였다.

• Journal of applied mathematics & informatics
• /
• 제29권1_2호
• /
• pp.211-225
• /
• 2011

In this paper, a class of bi-directional associative memory (BAM) fuzzy cellular neural networks with distributed delays and impulses is formulated and investigated. By employing an integro-differential inequality with impulsive initial conditions and the topological degree theory, some sufficient conditions ensuring the existence and global exponential stability of equilibrium point for impulsive BAM fuzzy cellular neural networks with distributed delays are obtained. In particular, the estimate of the exponential convergence rate is also provided, which depends on the delay kernel functions and system parameters. It is believed that these results are significant and useful for the design and applications of BAM fuzzy cellular neural networks. An example is given to show the effectiveness of the results obtained here.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 전기.전자공학 학술대회 논문집
• /
• pp.410-413
• /
• 1988

In this paper, the real-time optical associative memory using multiple hologram which is generated with two angular multiplexed reference beams and Fourier transformed object beam in the $BaTiO_{3}$ crystal based on DFWM mechanism. When one image is recorded in the $BaTiO_{3}$ crystal, complete image can be recalled by 9 % partial input of the stored original image without any additional thresholding and optical feedback process. As an experimental result of multiple Fourier hologram which is recorded with two binary images, OHCHAS and PARKHK, we can obtain complete image recalled by 1/6 partial input of the stored image.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1356-1358
• /
• 1996

Hopfield's suggestion of a neural network model for associative memory aroused the interest of many scientists and led to efforts of mathematical analyses. But the Hopfield Network has several disadvantages such as spurious states and capacity limitation. In that sense many scientists and engineers are trying to use a new optimization algorithm called genetic algorithm. But it is hard to use this algorithm in Hopfileld Network because of the fixed architecture. In this paper we introduce another method to determine the weight of Hopfield type network using Genetic Algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.22.3-22
• /
• 2001

An attention task, in which context information should be extracted from the first presented pattern, and the recognition answer of the second presented pattern should be generated using the context information, is employed in this paper. An Elman-type recurrent neural network is utilized to extract and keep the context information. A reinforcement signal that indicates whether the answer is correct or not, is only a signal that the system can obtain for the learning. Only by this learning, necessary context information became to be extracted and kept, and the system became to generate the correct answers. Furthermore, the function of an associative memory is observed in the feedback loop in the Elman-type neural network.

• 한국정밀공학회지
• /
• 제10권1호
• /
• pp.77-88
• /
• 1993

In this paper, we propose a stereo vision system to solve correspondence problem with large disparity and sudden change in environment which result from small distance between camera and working objects. First of all, a specific feature is divided by predfined elementary feature. And then these are combined to obtain coded data for solving correspondence problem. We use Neural Network to extract elementary features from specific feature and to have adaptability to noise and some change of the shape. Fourier transformation and Log-polar mapping are used for obtaining appropriate Neural Network input data which has a shift, scale, and rotation invariability. Finally, we use associative memory to obtain coded data of the specific feature from the combination of elementary features. In spite of specific feature with some variation in shapes, we could obtain satisfactory 3-dimensional data from corresponded codes.