Mofrad Asieh Abolpour, Parker Matthew G
Selmer Center, Department of Informatics, University of Bergen, Bergen 5020, Norway
Neural Comput. 2017 Jun;29(6):1681-1695. doi: 10.1162/NECO_a_00964. Epub 2017 Apr 14.
Clique-based neural associative memories introduced by Gripon and Berrou (GB), have been shown to have good performance, and in our previous work we improved the learning capacity and retrieval rate by local coding and precoding in the presence of partial erasures. We now take a step forward and consider nested-clique graph structures for the network. The GB model stores patterns as small cliques, and we here replace these by nested cliques. Simulation results show that the nested-clique structure enhances the clique-based model.
由格里蓬和贝鲁（GB）提出的基于团的神经联想记忆已被证明具有良好的性能，并且在我们之前的工作中，我们通过局部编码和预编码在存在部分擦除的情况下提高了学习能力和检索率。现在我们更进一步，考虑网络的嵌套团图结构。GB模型将模式存储为小团，我们在此用嵌套团替换这些小团。仿真结果表明，嵌套团结构增强了基于团的模型。
