Bidirectional Associative Memory Model Research Articles

New Insights on Bidirectional Associative Memory Neural Networks with Leakage Delay Components and Time-Varying Delays Using Sampled-Data Control

The sampling data control of bidirectional associative memory (BAM) neural network with leakage delay is considered in this article. The BAM model is viewed as a mixed delay that combines a distributed delay, a discrete delay that varies over time, and a delay in the leaking period. The sampling system is then converted to a continuous time-delay system using an input delay method. In order to get adequate conditions in the form of linear matrix inequalities(LMIs), we build a new Lyapunov-Krasovskii Functional (LKF) in conjunction with the free weight matrix approach. Finally, a simulation results are given to show the efficiency of the theoretical approach.

A multilayered bidirectional associative memory model for learning nonlinear tasks

A multilayered bidirectional associative memory neural network is proposed to account for learning nonlinear types of association. The model (denoted as the MF-BAM) is composed of two modules, the Multi-Feature extracting bidirectional associative memory (MF), which contains various unsupervised network layers, and a modified Bidirectional Associative Memory (BAM), which consists of a single supervised network layer. The MF generates successive feature patterns from the original inputs. These patterns change the relationship between the inputs and targets in a way that the BAM can learn. The model was tested on different nonlinear tasks, such as the N-bit, Double Moon and its variants, and the 3-class spiral task. Behaviors were reported through learning errors, decision zones, and recall performances. Results showed that it was possible to learn all tasks consistently. By manipulating the number of units per layer and the number of unsupervised network layers in the MF, it was possible to change the level of nonlinearity observed in the decision boundaries. Furthermore, results indicated that different behaviors were achieved from the same set of inputs by using the different generated patterns. These findings are significant as they showed how a BAM-inspired model could solve nonlinear tasks in a more cognitively plausible fashion.

Exponential stability of positive neural networks in bidirectional associative memory model with delays

This paper is concerned with the problem of exponential stability of positive neural networks in bidirectional associative memory (BAM) model with multiple time‐varying delays and nonlinear self‐excitation rates. On the basis of a systematic approach involving extended comparison techniques via differential inequalities, we first prove the positivity of state trajectories initializing from a positive cone called the admissible set of initial conditions. In combination with the use of Brouwer's fixed point theorem and M‐matrix theory, we then derive conditions for the existence and global exponential stability of a unique positive equilibrium of the model. An extension to the case of BAM neural networks with proportional delays is also presented. The effectiveness of the obtained results is illustrated by a numerical example with simulations.

Dynamics of BAM neural networks with mixed delays and leakage time‐varying delays in the weighted pseudo–almost periodic on time‐space scales

Bidirectional associative memory models are 2‐layer heteroassociative networks. In this work, we prove the existence and the global exponential stability of the unique weighted pseudo–almost periodic solution of bidirectional associative memory neural networks with mixed time‐varying delays and leakage time‐varying delays on time‐space scales. Some sufficient conditions are given for the existence, the convergence, and the global exponential stability of the weighted pseudo–almost periodic solution by using fixed‐point theorem and differential inequality techniques. The results of this paper complement the previous outcomes. An example is given to show the effectiveness of the derived results via computer simulations.

Design of state estimator for bidirectional associative memory neural networks with leakage delays

This paper considers the issue of state estimation for a class of bidirectional associative memory (BAM) neural networks. More precisely, the BAM model is considered with mixed delays which includes a constant delay in the leakage term, time-varying discrete delay and constant distributed delay. By constructing a novel Lyapunov–Krasovskii functional (LKF) together with free-weighting matrix technique, a new delay dependent sufficient condition is derived to estimate the neuron states through available output measurements such that, for all admissible delay bounds, the resulting estimation error system is globally asymptotically stable. Also it is assumed that the derivative of time delay is not necessarily zero or less than one. Further the derived conditions are formulated in terms of a set of linear matrix inequalities (LMIs) which can be easily solved by using some standard numerical packages. Finally a numerical example with simulation result is presented to show the effectiveness of the proposed theory. The result reveals that the leakage delays have a destabilizing influence on the system and they cannot be ignored.

Comparative Study of Workplace Happiness of Men and Women Using Bidirectional Associative Memories (BAMS)

The rapid advancement in Technology, particularly in a modern office environment, a wide and vast range of information has become easily available at employees fingertips. So the minimum expectation of a modern workplace is to keep the employees motivated, innovative and happy. Happiness at work is far more than job satisfaction. Happy employees are better employees. Happiness is an entirely subjective feeling of well-being experienced by the person, characterized by the presence of positive emotions and the absence of negative emotions. In this paper we discuss about Workplace happiness of men and women using Bidirectional Associative Memory (BAMs). We see that happiness related to subjective well-being plays a vital role in workplace happiness. So we use Bidirectional Associative memories to study the impact of happiness related to subjective wellbeing in Workplace happiness. The first section gives the concept of Workplace happiness. The section two introduces the basic concept and definitions of Bidirectional Associative Memory (BAMs). The section three contains the adoption of BAM model in to the concept of workplace happiness. And section four gives the conclusion and suggestions.

Bidirectional associative memories

Bidirectional Associative Memories (BAM) are systems that allow to associate pairs of patterns. Once a memory has learned, patterns can be recalled in two directions. BAMs have many applications in pattern recognition and image processing. The aim of this survey is to present several models of BAM throughout time, since Kosko [1988] proposed the first model; followed by those works based on or inspired by it, trying to improve recall capacity; to some recent one-shot models—such as Morphological BAM and Alpha-Beta BAM—which are of particular interest, given their superior performance.

ASYMPTOTICALLY STABLE MULTI-VALUED MANY-TO-MANY ASSOCIATIVE MEMORY NEURAL NETWORK AND ITS APPLICATION IN IMAGE RETRIEVAL

As an important artificial neural network, associative memory model can be employed to mimic human thinking and machine intelligence. In this paper, first, a multi-valued many-to-many Gaussian associative memory model (M 3 GAM) is proposed by introducing the Gaussian unidirectional associative mem- ory model (GUAM) and Gaussian bidirectional associative memory model (GBAM) into Hattori et al's multi-module associative memory model ((MMA) 2 ). Second, the M 3 GAM's asymptotical stability is proved theoretically in both synchronous and asynchronous update modes, which ensures that the stored patterns become the M 3 GAM's stable points. Third, by substituting the general similarity metric for the negative squared Euclidean distance in M 3 GAM, the generalized multi- valued many-to-many Gaussian associative memory model (GM 3 GAM) is pre- sented, which makes the M 3 GAM become its special case. Finally, we investigate the M 3 GAM's application in association-based image retrieval, and the computer simulation results verify the M 3 GAM's robust performance.

BAM Learning of Nonlinearly Separable Tasks by Using an Asymmetrical Output Function and Reinforcement Learning

Most bidirectional associative memory (BAM) networks use a symmetrical output function for dual fixed-point behavior. In this paper, we show that by introducing an asymmetry parameter into a recently introduced chaotic BAM output function, prior knowledge can be used to momentarily disable desired attractors from memory, hence biasing the search space to improve recall performance. This property allows control of chaotic wandering, favoring given subspaces over others. In addition, reinforcement learning can then enable a dual BAM architecture to store and recall nonlinearly separable patterns. Our results allow the same BAM framework to model three different types of learning: supervised, reinforcement, and unsupervised. This ability is very promising from the cognitive modeling viewpoint. The new BAM model is also useful from an engineering perspective; our simulations results reveal a notable overall increase in BAM learning and recall performances when using a hybrid model with the general regression neural network (GRNN).

Performance analysis and comparison of a minimum interconnections direct storage model with traditional neural bidirectional memories

This study proposes an efficient and improved model of a direct storage bidirectional memory, improved bidirectional associative memory (IBAM), and emphasises the use of nanotechnology for efficient implementation of such large-scale neural network structures at a considerable lower cost reduced complexity, and less area required for implementation. This memory model directly stores the X and Y associated sets of M bipolar binary vectors in the form of (MxN(x)) and (MxN(y)) memory matrices, requires O(N) or about 30% of interconnections with weight strength ranging between +/-1, and is computationally very efficient as compared to sequential, intraconnected and other bidirectional associative memory (BAM) models of outer-product type that require O(N(2)) complex interconnections with weight strength ranging between +/-M. It is shown that it is functionally equivalent to and possesses all attributes of a BAM of outer-product type, and yet it is simple and robust in structure, very large scale integration (VLSI), optical and nanotechnology realisable, modular and expandable neural network bidirectional associative memory model in which the addition or deletion of a pair of vectors does not require changes in the strength of interconnections of the entire memory matrix. The analysis of retrieval process, signal-to-noise ratio, storage capacity and stability of the proposed model as well as of the traditional BAM has been carried out. Constraints on and characteristics of unipolar and bipolar binaries for improved storage and retrieval are discussed. The simulation results show that it has log(e) N times higher storage capacity, superior performance, faster convergence and retrieval time, when compared to traditional sequential and intraconnected bidirectional memories.

Alpha–Beta bidirectional associative memories: theory and applications

In this work a new Bidirectional Associative Memory model, surpassing every other past and current model, is presented. This new model is based on Alpha---Beta associative memories, from whom it inherits its name. The main and most important characteristic of Alpha---Beta bidirectional associative memories is that they exhibit perfect recall of all patterns in the fundamental set, without requiring the fulfillment of any condition. The capacity they show is 2min(n,m), being n and m the input and output patterns dimensions, respectively. Design and functioning of this model are mathematically founded, thus demonstrating that pattern recall is always perfect, with no regard to the trained pattern characteristics, such as linear independency, orthogonality, or Hamming distance. Two applications illustrating the optimal functioning of the model are shown: a translator and a fingerprint identifier.

A New Model of BAM: Alpha-Beta Bidirectional Associative Memories

Most models of Bidirectional associative memories intend to achieve that all trained pattern correspond to stable states; however, this has not been possible. Also, none of the former models has been able to recall all the trained patterns. In this work we introduce a new model of bidirectional associative memory which is not iterative and has no stability problems. It is based on the Alpha-Beta associative memories. This model allows, besides correct recall of noisy patterns, perfect recall of all trained patterns, with no ambiguity and no conditions. An example of fingerprint recognition is presented.

Alpha-Beta Bidirectional Associative Memories

Most models of Bidirectional associative memories intend to achieve that all trained pattern correspond to stable states; however, this has not been possible. Also, none of the former models has been able to recall all the trained patterns. In this work we introduce a new model of bidirectional associative memory which is not iterative and has no stability problems. It is based on the Alpha-Beta associative memories. This model allows perfect recall of all trained patterns, with no ambiguity and no conditions. An example of fingerprint recognition is presented.

Robust stability of interval bidirectional associative memory neural network with time delays.

In this paper, the conventional bidirectional associative memory (BAM) neural network with signal transmission delay is intervalized in order to study the bounded effect of deviations in network parameters and external perturbations. The resultant model is referred to as a novel interval dynamic BAM (IDBAM) model. By combining a number of different Lyapunov functionals with the Razumikhin technique, some sufficient conditions for the existence of unique equilibrium and robust stability are derived. These results are fairly general and can be verified easily. To go further, we extend our investigation to the time-varying delay case. Some robust stability criteria for BAM with perturbations of time-varying delays are derived. Besides, our approach for the analysis allows us to consider several different types of activation functions, including piecewise linear sigmoids with bounded activations as well as the usual C1-smooth sigmoids. We believe that the results obtained have leading significance in the design and application of BAM neural networks.

Generalized Associative Memory Models: Their Memory Capacities and Potential Application

The Hopfield and bi-directional associative memory (BAM) models are well developed and carefully studied models for associative memory that are patterned after the memory structure of the animal brain. Their basic limitation is that they can only perform associations between at most two sets of patterns. Several different models for generalized associative memory are proposed. These models are all extensions or generalizations of the Hopfield and BAM models that can perform multiple associations. Extensive software simulations are conducted to evaluate the different models, using the memory capacity as basis for comparing their performance. Lastly, potential application of these models as data fusion systems is explored.

Novel stability criteria for bidirectional associative memory neural networks with time delays

AbstractIn this paper, the bidirectional associative memory (BAM) neural network with axonal signal transmission delay is considered. This model is also referred to as a delayed dynamic BAM model. By combining a number of different Lyapunov functionals with the Razumikhin technique, some sufficient conditions for the existence of a unique equilibrium and global asymptotic stability of the network are derived. These results are fairly general and can be easily verified. Besides, the approach for the analysis allows one to consider several different types of activation functions, including piecewise linear sigmoids with bounded activations as well as C1‐smooth sigmoids. It is believed that these results are significant and convenient in the design and applications of BAM neural networks. Copyright © 2002 John Wiley & Sons, Ltd.

Improved bidirectional retrieval of sparse patterns stored by Hebbian learning

The Willshaw model is asymptotically the most efficient neural associative memory (NAM), but its finite version is hampered by high retrieval errors. Iterative retrieval has been proposed in a large number of different models to improve performance in auto-association tasks. In this paper, bidirectional retrieval for the hetero-associative memory task is considered: we define information efficiency as a general performance measure for bidirectional associative memory (BAM) and determine its asymptotic bound for the bidirectional Willshaw model. For the finite Willshaw model, an efficient new bidirectional retrieval strategy is proposed, the appropriate combinatorial model analysis is derived, and implications of the proposed sparse BAM for applications and brain theory are discussed. The distribution of the dendritic sum in the finite Willshaw model given by Buckingham and Willshaw [Buckingham, J., & Willshaw, D. (1992). Performance characteristics of associative nets. Network, 3, 407–414] allows no fast numerical evaluation. We derive a combinatorial formula with a highly reduced evaluation time that is used in the improved error analysis of the basic model and for estimation of the retrieval error in the naive model extension, where bidirectional retrieval is employed in the hetero-associative Willshaw model. The analysis rules out the naive BAM extension as a promising improvement. A new bidirectional retrieval algorithm — called crosswise bidirectional (CB) retrieval — is presented. The cross talk error is significantly reduced without employing more complex learning procedures or dummy augmentation in the pattern coding, as proposed in other refined BAM models [Wang, Y. F., Cruz, J. B., & Mulligan, J. H. (1990). Two coding strategies for bidirectional associative memory. IEEE Trans. Neural Networks, 1(1), 81–92; Leung, C.-S., Chan, L.-W., & Lai, E. (1995). Stability, capacity and statistical dynamics of second-order bidirectional associative memory. IEEE Trans. Syst. Man Cybern., 25(10), 1414–1424]. The improved performance of CB retrieval is shown by a combinatorial analysis of the first step and by simulation experiments: it allows very efficient hetero-associative mapping, as well as auto-associative completion for sparse patterns — the experimentally achieved information efficiency is close to the asymptotic bound. The different retrieval methods in the hetero-associative Willshaw matrix are discussed as Boolean linear optimization problems. The improved BAM model opens interesting new perspectives, for instance, in information retrieval it allows efficient data access providing segmentation of ambiguous user input, relevance feedback and relevance ranking. Finally, we discuss BAM models as functional models for reciprocal cortico–cortical pathways, and the implication of this for a more flexible version of Hebbian cell-assemblies.

A Neural Network Explanation of Posttraumatic Stress Disorder

An introduction to connectionistic neural networks and their importance for behavior therapists was provided by Tryon (1995a). This article shows that the bidirectional associative memory connectionistic neural networks model meets all four of Jones and Barlow’s (1990) requirements and all five of Brewin, Dalgleish, and Joseph’s (1996) requirements for a theoretical explanation of posttraumatic stress disorder (PTSD). The bidirectional associative memory model provides a theoretical basis for explaining the clinical symptom constellation of PTSD, with special emphasis on why trauma is re-experienced through memory; accounts for individual variation in symptom severity, including why some people do not develop PTSD; explains why persons with PTSD are comorbid with depression, generalized anxiety, and substance abuse; explains how abnormal behavior derives from normal memory formation processes; and makes novel predictions.

Qualitative analysis of Bi-directional Associative Memory with time delay

Bi-directional associative memory models are two-layer heteroassociative networks. In this paper, axonal signal transmission delay is introduced into BAM model yielding a class of generalized BAM networks. Conditions for the existence of equilibrium points, boundedness of trajectories and global stability are emphatically discussed for BAM with above-mentioned time delay. Circuit architecture of BAM with time delay is given. Correctness for our results is verified by using some examples and computer simulations. The obtained results have leading significance in the design and application of BAM networks. © 1998 John Wiley & Sons, Ltd.

Qualitative analysis of Bi‐directional Associative Memory with time delay

Bi-directional associative memory models are two-layer heteroassociative networks. In this paper, axonal signal transmission delay is introduced into BAM model yielding a class of generalized BAM networks. Conditions for the existence of equilibrium points, boundedness of trajectories and global stability are emphatically discussed for BAM with above-mentioned time delay. Circuit architecture of BAM with time delay is given. Correctness for our results is verified by using some examples and computer simulations. The obtained results have leading significance in the design and application of BAM networks. © 1998 John Wiley & Sons, Ltd.