APPLICATION OF BIDIRECTIONAL ASSOCIATIVE MEMORIES (BAM)

IEEE Computer Society, 2006

The Lernmatrix, which is the first known model of associative memory, is an heteroassociative memory, but it can also act as a binary pattern classifier depending on the choice of the output patterns. However, this model suffers two great problems: saturation and imperfect recall of some of the associations, even in the fundamental set, depending on the associations. In this work, a modification to the original Lernmatrix recall phase algorithm is presented. This modification improves the recalling capacity of the original model. Experimental results show this improvement

In this paper we find how stress makes an impact in imparting knowledge using Bidirectional associative memories. Since no statistical data to this effect can be collected, we using a linguistic questionnaire interviewed 50 persons, from the group of educationalists, NGOs, youth, teachers etc. and using these interviews constructed the FRM model, relating the effect of stress on the physical, mental and emotional balance while preparing the student to gain knowledge . We use BAM models to study, analyze this problem of stress management among the teachers to shape up our young minds in education.

IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 1998

paper proposes a general model for bidirectional associative memories that associate patterns between the X-space and the Y-space. The general model does not require the usual assumption that the interconnection weight from a neuron in the X-space to a neuron in the Yspace is the same as the one from the Y-space to the X-space. We start by de ning a supporting function to measure how well a state supports another state in a general bidirectional associative memory (GBAM). We then use the supporting function to formulate the associative recalling process as a dynamic system, explore its stability and asymptotic stability conditions, and develop an algorithm for learning the asymptotic stability conditions using the Rosenblatt perceptron rule. The e ectiveness of the proposed model for recognition of noisy patterns and the performance of the model in terms of storage capacity, attraction, and spurious memories are demonstrated by some outstanding experimental results. Keywords| bidirectional associative memory, asymmetrical memory, stability, asymptotic stability H. Shi and X. Zhuang are with the Computer Engineering and

2007

This paper* describes an innovative model of long term memory (SALT -Schema-Associative Long Term memory). It also presents an implementation of the SALT model, a specification of an agent, and some scenarios of interactions with the agent. The model presented has its roots in two of the most important general theories of human memory, namely the associative network theory and the schema-based theory. The main advantage of the SALT model is its capability of generating context-dependent cognition. The examples selected for illustrating the functioning of the implementation were chosen from the field of personnel evaluation.

Lecture Notes in Computer Science, 2006

Hebbian hetero-associative learning is inherently asymmetric. Storing a forward association from pattern A to pattern B enables the recalling of pattern B given pattern A. This, in general, does not allow the recalling of pattern A given pattern B. The forward association between A and B will tend to be stronger than the backward association between B and A. In this paper it is described how the dynamical associative model proposed in can be extended to create a bi-directional associative memory where forward association between A and B is equal to backward association between B and A. This implies that storing a forward association, from pattern A to pattern B, would enable the recalling of pattern B given pattern A and the recalling of pattern A given pattern B. We give some formal results that support the functioning of the proposal, and provide some examples were the proposal finds application.

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2014

Fuzzy Associative Memory (FAM) is a neural network that stores associations of patterns. The most important advantage of FAM is recalling stored patterns from noisy inputs (noise tolerance). Some FAMs only show associations or content of pattern separately. Therefore, we propose a model of FAM that shows both associations and content of patterns effectively. In learning process, each pair of pattern is learned by the minimum of input and output pattern. Then, all pairs of pattern are generalized by mean of the learning results of each pair. In recalling process, a new threshold is added to improve noise tolerance. We have conducted experiments in pattern recognition to prove the effectiveness of our FAM. Experiment results show that our model tolerates noise better than previous FAMs in two types of noise.

2015

Pattern association is one among the ways through which human brain stores and recalls information. From the literature, it is evident that cognitive abilities of human brain such as learning, memorizing, recalling and updating of information are performed via concepts and their connections. In this work we have made use of Formal Concept Analysis (FCA), a mathematical framework for data and knowledge processing, to represent memories and to perform some of the cognitive functions of human brain. In particular, we model the functionalities of bidirectional associative memories. The proposed model can learn, memorize the learnt information, bi-directionally recall the information that is associated with the presented cue with the help of object-attribute relations that exists in the scenario and update the knowledge when there is a change in the considered scenario. Also when a noisy cue is given, the model is capable of recalling the most closely associated pattern by exploiting the concept hierarchy principle of FCA. Similarly, when a new information is presented on a learnt scenario, the proposed model can update its knowledge by avoiding the need to re-learn scenario. We illustrate the proposed model with a case study and validate with experiments on few real world datasets.

IEEE Transactions on Neural Networks, 1994

An iterative learning algorithm called PRLAB is described for the discrete Bidirectional Associative Memory (BAM). Guaranteed recall of all training pairs is ensured by PRLAB. The proposed algorithm is significant in many ways. Unlike many existing iterative learning algorithms, PRLAB is not based on the gradient descent technique. It is a novel adaptation from the well-known relaxation method for solving a system of linear inequalities. The algorithm is very fast. Learning 200 random patterns in a 200-200 BAM takes only 20 epochs on the average. PRLAB is highly insensitive to learning parameters and the initial configuration of a BAM. It also offers high scalability for large applications by providing the same high performance when the number of training patterns are increased in proportion to the size of the BAM. An extensive performance analysis of the new learning algorithm is included. P M = c X (k) T y (k) k=l to store a set of vector pairs { (X (k) , Y (k)) } k = l ,. .. , p. The use of such a correlation matrix for storing information in a neural network model is often called the first-order correlation Manuscript

Lecture Notes in Medical Informatics, 1991

Neural networks are used as associative memories to build an expert system for diagnostic. Similarly to expert systems implemented using symbolic manipulation, here the knowledge is introduced by a knowledge engineer using a collection of known cases. Fuzzy sets are used as interpretation for connection values and/or excitation state of units. The main result is that the proposed neural network allows not only to find a solution in some cases, but also to suggest to obtain more clinical data if the data available is insufficient to conclude. To illustrate the approach the case of two diseases with similar symptoms (difficult diagnostic) is used.