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 1810.03370cs.LGcs.AImath.OCstat.ML
收藏

深度整流网络线性区域的经验界

Empirical Bounds on Linear Regions of Deep Rectifier Networks

Bucknell University(巴克内尔大学);The University of Utah(犹他大学)

Thiago Serra, Srikumar Ramalingam

摘要:

我们可以通过线性区域的数量来比较使用整流线性单元(ReLU)的神经网络的表达能力,线性区域的数量反映了由这种网络建模的分段线性函数的数量。然而,枚举这些区域是禁止的,并且已知的分析界限对于具有相同维度的网络是相同的。在这项工作中,我们通过基于训练网络特征和概率推理的经验边界来近似线性区域的数量。我们的第一个贡献是使用通用哈希函数对ReLU定义的激活模式进行采样的方法。该方法基于网络的混合线性规划(MILP)公式和MILP解集的概率下界算法(我们称之为MIPBound),该算法比精确计数快得多,并达到类似数量级的值。我们的第二个贡献是对线性区域的最大数量有一个更严格的基于激活的界限,这在具有窄层的网络中特别强。结合起来,这些边界产生了深度神经网络的线性区域数量的快速代理。

英文摘要:

We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However, enumerating these regions is prohibitive and the known analytical bounds are identical for networks with same dimensions. In this work, we approximate the number of linear regions through empirical bounds based on features of the trained network and probabilistic inference. Our first contribution is a method to sample the activation patterns defined by ReLUs using universal hash functions. This method is based on a Mixed-Integer Linear Programming (MILP) formulation of the network and an algorithm for probabilistic lower bounds of MILP solution sets that we call MIPBound, which is considerably faster than exact counting and reaches values in similar orders of magnitude. Our second contribution is a tighter activation-based bound for the maximum number of linear regions, which is particularly stronger in networks with narrow layers. Combined, these bounds yield a fast proxy for the number of linear regions of a deep neural network.

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。

↑