arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.08930cs.LGcond-mat.dis-nnstat.ML
收藏

用深层机计算的函数空间

Space of Functions Computed by Deep-Layered Machines

London Institute for Mathematical Sciences(伦敦数学科学研究所);Aston University(阿斯顿大学)

Alexander Mozeika, Bo Li, David Saad

摘要:

我们研究随机分层机器计算的函数空间,包括深度神经网络和布尔电路。通过研究递归和层依赖结构上计算的布尔函数的分布,我们发现在两种模型中是相同的。根据所使用的初始条件和计算元素,我们描述了在大深度极限下计算的函数空间,并表明布尔函数的宏观熵随着深度的增加单调增加或减少。

英文摘要:

We study the space of functions computed by random-layered machines, including deep neural networks and Boolean circuits. Investigating the distribution of Boolean functions computed on the recurrent and layer-dependent architectures, we find that it is the same in both models. Depending on the initial conditions and computing elements used, we characterize the space of functions computed at the large depth limit and show that the macroscopic entropy of Boolean functions is either monotonically increasing or decreasing with the growing depth.

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。

↑