Designing architectures of convolutional neural networks to solve practical problems
Designing architectures of convolutional neural networks to solve practical problems
复制标题
DOI：
10.1016/j.eswa.2017.10.052
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
M. D. Ferreira;D. C. Corrêa;L. G. Nonato;R. Mello
中科院分区：
文献类型：
--
作者：
M. D. Ferreira;D. C. Corrêa;L. G. Nonato;R. Mello
卷积神经网络（CNN）是最先进的深度学习（DL）算法之一，因为它具有支持数据移动、规模变化的鲁棒性，以及从大规模输入数据中提取相关信息的能力。然而，设置适当的参数来定义CNN架构仍然是一个具有挑战性的问题，主要是为了解决现实世界的问题。一种典型的方法是对不同的CNN设置进行经验评估，以选择最合适的设置。这个过程有明显的局限性，包括选择合适的预定义配置以及评估每个配置所涉及的高计算成本。这项工作提出了一种新的方法来解决前面提到的问题，提供了估计有效CNN配置的机制，包括卷积掩模（卷积核）的大小和每层卷积单元（CNN神经元）的数量。该方法基于动态系统领域的知名工具假近邻（False Nearest Neighbors， FNN），有助于估计不那么复杂的CNN架构，并产生良好的结果。我们的实验证实，通过提出的方法估计的架构与由经验和计算密集型策略定义的复杂架构一样有效。
The Convolutional Neural Network (CNN) figures among the state-of-the-art Deep Learning (DL) algorithms due to its robustness to support data shift, scale variations, and its capability of extracting relevant information from large-scale input data. However, setting appropriate parameters to define CNN architectures is still a challenging issue, mainly to tackle real-world problems. A typical approach consists in empirically assessing different CNN settings in order to select the most appropriate one. This procedure has clear limitations, including the choice of suitable predefined configurations as well as the high computational cost involved in evaluating each of them. This work presents a novel methodology to tackle the previously mentioned issues, providing mechanisms to estimate effective CNN configurations, including the size of convolutional masks (convolutional kernels) and the number of convolutional units (CNN neurons) per layer. Based on the False Nearest Neighbors (FNN), a well-known tool from the area of Dynamical Systems, the proposed method helps estimating CNN architectures that are less complex and produce good results. Our experiments confirm that architectures estimated through the proposed approach are as effective as the complex ones defined by empirical and computationally intensive strategies.