• Korean Journal of Optics and Photonics
• /
• v.3 no.3
• /
• pp.191-197
• /
• 1992

We have developed a new optical associative memory system hased on the symmetric three layered neural network model, uhing two holograms and a LCIV. In the experiment, four Korean alphabet letters (ㄹ, ㅅ, ㅇ, ㅈ) are used as memory patterns. The results are compared with those of the two layered network and the IIopfield models. The results show that more than 95% recognition ablity is obtained for thc input which has the error rate less than 12%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.241-242
• /
• 2012

큰 데이터 트래픽을 일으키는 I/O 작업을 수행할 경우에 많은 디스크 접근과 데이터 처리가 발생하며 이는 컴퓨팅 성능의 하락을 일으킨다. 이를 위해 메모리와 디스크 사이에 버퍼 역할을 하는 페이지 캐시 기법이 사용된다. 그러나 LRU 를 사용하는 페이지 캐시의 특성상, 많은 양의 데이터가 한번만 접근되고 다시 사용되지 않는다면 성능상의 큰 효과가 없다. 본 논문에서는 집합 연상 페이지 캐시에 오염 버퍼를 둠으로써, 재사용되지 못하고 페이지 캐시의 크기만 커지는 현상을 최소화시켜 I/O 성능을 개선시킬 수 있는 방법을 제안한다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.37-45
• /
• 2006

In this paper, we propose the development of MHLA(Modulatory Hippocampus Learning Algorithm) which remodel a principle of brain of hippocampus. Hippocampus takes charge auto-associative memory and controlling functions of long-term or short-term memory strengthening. We organize auto-associative memory based 3 steps system(DG, CA3, CAl) and improve speed of learning by addition of modulator to long-term memory learning. In hippocampal system, according to the 3 steps order, information applies statistical deviation on Dentate Gyrus region and is labelled to responsive pattern by adjustment of a good impression. In CA3 region, pattern is reorganized by auto-associative memory. In CAI region, convergence of connection weight which is used long-term memory is learned fast by neural networks which is applied modulator. To measure performance of MHLA, PCA(Principal Component Analysis) is applied to face images which are classified by pose, expression and picture quality. Next, we calculate feature vectors and learn by MHLA. Finally, we confirm cognitive rate. The results of experiments, we can compare a proposed method of other methods, and we can confirm that the proposed method is superior to the existing method.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2004.06a
• /
• pp.15-24
• /
• 2004

본 논문은 be동사에 관한 학생들의 영어개념 이해에서 발생되는 오인을 진단할 수 잇는 학습오인 진단 시스템을 제시한다. 학습오인 진단 시스템에서 퍼지 인진 맵은 영어에 대한 학생들이 가지는 선입개념들과 오인들을 인과관계로 표현하며, 개념간의 인과관계를 기억할 수 있는 퍼지 연상 메모리를 통하여 오인의 원인들을 진단한다. 본 연구는 기존의 학습 오인을 진단하는 규칙기반 전문가 시스템의 한계성을 극복할 수 있는 새로운 방법을 제공하며, 교육분야의 다양한 영역에서 학습자들의 학습 진단을 위한 학습오인 진단 시스템으로 적용될 수 있다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.9
• /
• pp.1102-1107
• /
• 1988

We describe a volume holographic associative memory using photorefractive material and conventional planar mirror. Multiple hologram is generated with two angular multiplexed writing beams and Fourier transformed object beam in Ba Ti O3 crystal at 0.6328 um. Complete image can be recalled successfully by partial input of the original stored image without any additional thresholding and optical feedback process. It is proved that our system is useful for optical implementation of real-time associative memory and location addressable memory.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.69-72
• /
• 2001

In this paper, we propose a new design method for bidirectional associative memories model with high error correction ratio. We extend the conventional GBAM model using bias terms and formulate a design procedure in the form of a constrained optimization problem. The constrained optimization problem is then transformed into a GEVP(generalized eigenvalue problem), which can be efficiently solved by recently developed interior point methods. The effectiveness of the proposed approach is illustrated by a example.

• Information and Communications Magazine
• /
• v.7 no.3
• /
• pp.27-34
• /
• 1990

The $(L,\psi)$ feature description on the binary boundary air craft image is introduced of classifying 3-D object (aircraft) identification. Three types for associative matrix memories are employed and tested for their classification performance. The fast association involved in these memories can be implemented using a parallel optical matrix-vector operation. Two associative memories are based on pseudoinverse solutions and the third one is interoduced as a paralell version of a nearest-neighbor classifier. Detailed simulation results for each associative processor are provided.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2872-2875
• /
• 1999

본 논문은 주어진 적합한 이진 패턴들의 집합이 점근적으로 안정한 평형점들로써 저장되는 최적으로 성능을 갖는 GBSB (generalized brain-state-in-a-box)의 설계가 고려된다. GBSB 모델의 정성적 특성에 기초하여, 설계 문제가 제약 조건을 가한 최적화 문제로 공식화된다. 다음으로, 우리는 이 문제를 GEVP (generalized eigenvalue Problem)라고 불리는 최적화 문제로 변환한다. 제안된 방법을 예증하기 위함과 기존의 방법과의 비교를 위해서 설계 예제가 주어진다.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.463-472
• /
• 2000

In this paper, we consider the problem of realizing associative memories via cellular neural network(CNN). After introducing qualitative properties of the CNN model, we formulate the synthesis of CNN that can store given binary vectors with optimal performance as a constrained optimization problem. Next, we observe that this problem's constraints can be transformed into simple inequalities involving linear matrix inequalities(LMIs). Finally, we reformulate the synthesis problem as a generalized eigenvalue problem(GEVP), which can be efficiently solved by recently developed interior point methods. Proposed method can be applied to both space varying template CNNs and space-invariant template CNNs. The validity of the proposed approach is illustrated by design examples.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.7
• /
• pp.1-9
• /
• 2011

Memristor is a portmanteau of "memory resistor". The resistance of memristor is changed depends on the history of electric charge that passed through the device and it is able to memorize the last resistance after turning off the power supply. This paper presents this device that has a high chance to be the next generation of commercial non-volatile memory and its behavior modeling using SPICE simulation. The memristor MOS content addressable memory (M_CAM) is also designed and simulated using the proposed behavioral model. The proposed M_CAM unit cell area and power consumption show an improvement around 40% and 96%, respectively, compare to the conventional SRAM based CAMs. The M_CAM layout is also implemented using 0.13${\mu}m$ mixed-signal CMOS process under 1.2 V supply voltage.