• Journal of Information Processing Systems
• /
• 제13권3호
• /
• pp.435-447
• /
• 2017

Associative and bidirectional associative memories are examples of associative structures studied intensively in the literature. The underlying idea is to realize associative mapping so that the recall processes (one-directional and bidirectional ones) are realized with minimal recall errors. Associative and fuzzy associative memories have been studied in numerous areas yielding efficient applications for image recall and enhancements and fuzzy controllers, which can be regarded as one-directional associative memories. In this study, we revisit and augment the concept of associative memories by offering some new design insights where the corresponding mappings are realized on the basis of a related collection of landmarks (prototypes) over which an associative mapping becomes spanned. In light of the bidirectional character of mappings, we have developed an augmentation of the existing fuzzy clustering (fuzzy c-means, FCM) in the form of a so-called collaborative fuzzy clustering. Here, an interaction in the formation of prototypes is optimized so that the bidirectional recall errors can be minimized. Furthermore, we generalized the mapping into its granular version in which numeric prototypes that are formed through the clustering process are made granular so that the quality of the recall can be quantified. We propose several scenarios in which the allocation of information granularity is aimed at the optimization of the characteristics of recalled results (information granules) that are quantified in terms of coverage and specificity. We also introduce various architectural augmentations of the associative structures.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.936-939
• /
• 1996

In this paper, two specially designed associative mapping memories, called Associative Mapping Elements(AME) and Multiple-Digit Overlapping AME(MDO-AME), are presented for learning of nonlinear functions including kinematics and dynamics of robot manipulators. The proposed associative mapping memories consist of associative mapping rules(AMR) and weight update rules(WUR) which guarantee generalization and specialization of input-output relationship of learned nonlinear functions. Two simulation results, one for supervised learning and the other for unsupervised learning, are given to demonstrate the effectiveness of the proposed associative mapping memories.

• 정보와 통신
• /
• 제7권3호
• /
• 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.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 춘계학술대회 학술발표 논문집
• /
• 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.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.409-412
• /
• 1997

In this paper, we propose a novel synthesis method of GBSB(Generalized BSB)-based neural autoassociative memories in which we analyze qualitative properties of GBSB model, recast a design problem of an associative memory to LMIP(Linear Matrix Inequality Problem), and optimize the LMIP using LMI techniques. The obtained memory satisfies many of the required properties of associative memories and has some peculiar properties. Comparing experimental results with those of others, we show its correctness and effectiveness.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.482-482
• /
• 2000

The essential requirements of neural network for human skill transfer are fast convergence, high storage capacity, and strong noise immunity. Bidirectional associative memory(BAM) suffering from low storage capacity and abundance of spurious memories is rarely used for skill transfer application though it has fast and wide association characteristics for visual data. This paper suggests generalization of classical BAM structure and new learning algorithm which uses supervised learning to guarantee perfect recall starting with correlation matrix. The generalization is validated to accelerate convergence speed, to increase storage capacity, to lessen spurious memories, to enhance noise immunity, and to enable multiple association using simulation work.

• 한국지능시스템학회논문지
• /
• 제25권1호
• /
• pp.97-104
• /
• 2015

An 'associative cube', a class of auto-associative memories, is revisited here, in which training data and hidden orthogonal basis functions such as wavelet packets or Fourier kernels, are combined in the weight cube. This weight cube has hidden units in its depth, represented by a three dimensional cubic structure. We develop an unsupervised incremental learning mechanism based upon the adaptive least squares method. Training data are mapped into orthogonal basis vectors in a least-squares sense by updating the weights which minimize an energy function. Therefore, a prescribed orthogonal kernel is incrementally assigned to an incoming data. Next, we show how a decoding procedure finds the closest one with a competitive network in the hidden layer. As noisy test data are applied to an associative cube, the nearest one among the original training data are restored in an optimal sense. The simulation results confirm robustness of associative cubes even if test data are heavily distorted by various types of noise.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1050-1052
• /
• 1987

This study presents mental model based on cognitive psychology and deals with implementation of associative comparator using learning automata with random access memories.

• 한국지능시스템학회논문지
• /
• 제11권7호
• /
• pp.680-688
• /
• 2001

In this paper, we propose a reliable method for searching the optimally performing generalized brain-state-in-a-box (GBSB) neural associative memory using an evolution program (EP) given a set of prototype patterns to be stored as stable equilibrium points. First, we exploit some qualitative guidelines necessary to synthesize the GBSB model. Next, we parameterize the solution space utilizing the limited number of parameters to represent the solution space. Then, we recast the synthesis of GBSB neural associative memories as two constrained optimization problems, which are equivalent to finding a solution to the original synthesis problem. Finally, we employ an evolution program (EP), which enables us to find an optimal set of parameters related to the size of domains of attraction (DOA) for prototype patterns. The validity of this approach is illustrated by a design example and computer simulations.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.43.5-43
• /
• 2001

This paper considers a new synthesis of the optimally performing brain-state-in-a-box (BSB) neural associative memory given a set of prototype patterns to be stored as asymptotically stable equilibrium points with the large and uniform size of the domain of attraction (DOA). First, we propose a new theorem that will be used to provide a guideline in design of the BSB neural associative memory. Finally, a design example is given to illustrate the proposed approach and to compare with existing synthesis methods.