Alpha---Beta bidirectional associative memories: theory and applications
Neural Processing Letters
A Bidirectional Hetero-Associative Memory for True-Color Patterns
Neural Processing Letters
IEEE Transactions on Neural Networks
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Color image associative memory on a class of Cohen-Grossberg networks
Pattern Recognition
A new bi-directional associative memory
MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence
A Chaotic Feature Extracting BAM and Its Application in Implementing Memory Search
Neural Processing Letters
A new learning strategy of general BAMs
MLDM'12 Proceedings of the 8th international conference on Machine Learning and Data Mining in Pattern Recognition
Bidirectional associative memories: Different approaches
ACM Computing Surveys (CSUR)
| Hi-index | 0.00 |
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.