arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv cs/0506078cs.IRcs.NE
收藏

动态神经网络:信息与拓扑

Dynamical Neural Network: Information and Topology

David Dominguez, Kostadin Koroutchev, Eduardo Serrano, Francisco B. Rodriguez

摘要:

如果神经网络具有大的存储容量并且检索的质量足够好,那么它就可以作为联想记忆设备工作。网络的学习能力和吸引能力都可以用模式与检索状态之间的互信息来度量。本文讨论了Hebb网络在最大MI意义下的最优拓扑。我们使用小世界拓扑。连接性$γ$的范围从极度稀释到完全连接的网络;随机性$ω$的范围从纯本地到完全随机的邻居。研究发现,虽然稳定性意味着在$γ_{opt}(ω)\to 0$的最佳$MI(γ,ω)$,对于动力学,最佳拓扑保持在一定的$γ_{opt}>0$时,只要$0\leqω<0.3$。

英文摘要:

A neural network works as an associative memory device if it has large storage capacity and the quality of the retrieval is good enough. The learning and attractor abilities of the network both can be measured by the mutual information (MI), between patterns and retrieval states. This paper deals with a search for an optimal topology, of a Hebb network, in the sense of the maximal MI. We use small-world topology. The connectivity $γ$ ranges from an extremely diluted to the fully connected network; the randomness $ω$ ranges from purely local to completely random neighbors. It is found that, while stability implies an optimal $MI(γ,ω)$ at $γ_{opt}(ω)\to 0$, for the dynamics, the optimal topology holds at certain $γ_{opt}>0$ whenever $0\leqω<0.3$.

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。

↑