在神经团网络中存储非均匀分布的消息
Storing non-uniformly distributed messages in networks of neural cliques
AI总结:
研究提出在稀疏联想记忆中高效存储非均匀消息的策略,分析方法并展示实际应用。
摘要:
关联记忆是一种数据结构,允许从存储消息的部分内容中检索信息。它们类似于人脑,例如能根据歌曲的开头找回结尾。在不同的联想记忆家族中,稀疏型以其存储位数与使用的位数比最优而著称。然而,已知存储消息的非均匀性会导致性能显著下降。本文介绍了几种策略,以在最近引入的稀疏联想记忆中高效存储非均匀消息。我们分析并讨论了所介绍的方法,并展示了实际应用示例。
英文摘要:
Associative memories are data structures that allow retrieval of stored messages from part of their content. They thus behave similarly to human brain that is capable for instance of retrieving the end of a song given its beginning. Among different families of associative memories, sparse ones are known to provide the best efficiency (ratio of the number of bits stored to that of bits used). Nevertheless, it is well known that non-uniformity of the stored messages can lead to dramatic decrease in performance. We introduce several strategies to allow efficient storage of non-uniform messages in recently introduced sparse associative memories. We analyse and discuss the methods introduced. We also present a practical application example.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。