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 0710.0213cs.NEcs.AI
收藏

优化复杂神经网络的拓扑结构

Optimising the topology of complex neural networks

INRIA Futurs(法国国家信息与自动化研究所未来分部)

Fei Jiang, Hugues Berry, Marc Schoenauer

摘要:

本文研究了复杂神经网络,即具有复杂拓扑结构的神经网络。本文采用自组织映射神经网络对手写体数字进行分类,神经网络的n个邻域关系由一个复杂网络定义。我们表明,拓扑结构对神经元故障的性能和鲁棒性有很小的影响,至少在长的学习时间。然而,通过网络拓扑的人工进化,性能可能会提高(几乎10%)。在我们的实验条件下,进化后的网络比它们的父母更随机,但显示出更异质的度分布。

英文摘要:

In this paper, we study instances of complex neural networks, i.e. neural netwo rks with complex topologies. We use Self-Organizing Map neural networks whose n eighbourhood relationships are defined by a complex network, to classify handwr itten digits. We show that topology has a small impact on performance and robus tness to neuron failures, at least at long learning times. Performance may howe ver be increased (by almost 10%) by artificial evolution of the network topo logy. In our experimental conditions, the evolved networks are more random than their parents, but display a more heterogeneous degree distribution.

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。

↑