A Bidirectional Heteroassociative Memory for Binary and Grey-Level Patterns

Abstract

Abstract-Typical bidirectional associative memories (BAM) use an offline, one-shot learning rule, have poor memory storage capacity, are sensitive to noise, and are subject to spurious steady states during recall. Recent work on BAM has improved network performance in relation to noisy recall and the number of spurious attractors, but at the cost of an increase in BAM complexity. In all cases, the networks can only recall bipolar stimuli and, thus, are of limited use for grey-level pattern recall. In this paper, we introduce a new bidirectional heteroassociative memory model that uses a simple self-convergent iterative learning rule and a new nonlinear output function. As a result, the model can learn online without being subject to overlearning. Our simulation results show that this new model causes fewer spurious attractors when compared to others popular BAM networks, for a comparable performance in terms of tolerance to noise and storage capacity. In addition, the novel output function enables it to learn and recall grey-level patterns in a bidirectional way.

Systems Factorial Technology Explained to Humans

“…Finally, Tremblay, Harding, Chartier, and Cousineau (2014) recently applied the SFT methodology to the recall process of an architecture that is not one of the five detected by SFT, the Bidirectional Heteroassociative Memory, or BHM (Chartier & Boukadoum, 2006). The BHM uses a series of iterations of parallel units until activations stabilize to select response units.…”

Multiple Fault Location in a Photovoltaic Array Using Bidirectional Hetero-Associative Memory Network in Micro-distribution Systems

“…A BHAM network is a feedback pattern mechanism that allows for the generation of new patterns, noise filtering, and pattern completion [14,16]. It has a network that contains an input layer, output layer, and network connections, as shown in Figure 4.…”

“…Based on an electrical examination, this study proposes use of the bidirectional hetero-associative memory (BHAM) network [14][15][16][17] to detect multiple faults in a PV array. The BHAM network can store the training patterns in a connecting matrix when modeling the human cognitive process [16].…”

“…In addition, BHAM is able to learn and recall various types of input and output associations. The proposed modified configuration with the hidden layer is used to solve nonlinear separable problems [14], and its manner can deal with inputs and outputs using binary, 3 bipolar, or numerical data. Using nonlinear output feedback, it can also act using biological behavior in the form of hetero-associative memories for different data types and data lengths.…”

RF-LNA circuit synthesis by genetic algorithm-specified artificial neural network

“…Among other kinds of ANNs, one has recently shown encouraging signs for circuit synthesis applications: the bidirectional associative memories (BAM) [8]. When set up for heteroassociative operation, it appears to have the potential to reconstruct the exemplar that led to a category label [9]. This process is similar to finding a circuit component values given a set of performance specifications.…”