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 1809.10073cs.LGstat.ML
收藏

通过状态分布重新发现深度神经网络

Rediscovering Deep Neural Networks Through Finite-State Distributions

University of Central Florida(中佛罗里达大学)

Amir Emad Marvasti, Ehsan Emad Marvasti, George Atia, Hassan Foroosh

摘要:

我们提出了一种思考深度神经网络的新方法,其中网络的线性和非线性组件是自然导出的,并根据概率论原理进行了证明。特别是,在我们的框架中构建的模型将概率分配给不确定的实现,导致Kullback-Leibler发散(KLD)作为线性层。在我们的模型构建中,我们还得到了一个类似于贝叶斯定理支持的ReLU激活的结构。我们框架中的非线性是规范化层,使用ReLU和Sigmoid作为元素近似。此外,池化函数是根据框架的力学推导出的空间随机变量的边缘化。因此,Max Pooling近似于上述边缘化过程。由于我们的模型由有限状态分布(FSD)作为变量和参数组成,因此可以精确计算熵和KLD等信息理论量,从而提供更客观的测量来分析网络。与现有的依赖于神经网络的设计不同,所提出的框架限制了对CNN的主观解释,并从一个全新的角度揭示了神经网络的功能。

英文摘要:

We propose a new way of thinking about deep neural networks, in which the linear and non-linear components of the network are naturally derived and justified in terms of principles in probability theory. In particular, the models constructed in our framework assign probabilities to uncertain realizations, leading to Kullback-Leibler Divergence (KLD) as the linear layer. In our model construction, we also arrive at a structure similar to ReLU activation supported with Bayes' theorem. The non-linearities in our framework are normalization layers with ReLU and Sigmoid as element-wise approximations. Additionally, the pooling function is derived as a marginalization of spatial random variables according to the mechanics of the framework. As such, Max Pooling is an approximation to the aforementioned marginalization process. Since our models are comprised of finite state distributions (FSD) as variables and parameters, exact computation of information-theoretic quantities such as entropy and KLD is possible, thereby providing more objective measures to analyze networks. Unlike existing designs that rely on heuristics, the proposed framework restricts subjective interpretations of CNNs and sheds light on the functionality of neural networks from a completely new perspective.

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。

↑