当前位置: X-MOL 学术Phys. Rev. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Space of Functions Computed by Deep-Layered Machines
Physical Review Letters ( IF 8.6 ) Pub Date : 2020-10-12 , DOI: 10.1103/physrevlett.125.168301
Alexander Mozeika , Bo Li , David Saad

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.

中文翻译:

深度机器计算的功能空间

我们研究了由随机层级机器(包括深度神经网络和布尔电路)计算的函数空间。研究在循环和依赖于层的体系结构上计算的布尔函数的分布,我们发现在两个模型中它是相同的。根据初始条件和所使用的计算元素,我们表征了在较大深度极限处计算的函数的空间,并表明布尔函数的宏观熵随深度的增加而单调增加或减少。
更新日期:2020-10-12
down
wechat
bug