The deep learning literature is continuously updated with new architectures and training techniques. However, weight initialization is overlooked by most recent research, despite some intriguing findings regarding random weights. On the other hand, recent works have been approaching Network Science to understand the structure and dynamics of Artificial Neural Networks (ANNs) after training. Therefore, in this work, we analyze the centrality of neurons in randomly initialized networks. We show that a higher neuronal strength variance may decrease performance, while a lower neuronal strength variance usually improves it. A new method is then proposed to rewire neuronal connections according to a preferential attachment (PA) rule based on their strength, which significantly reduces the strength variance of layers initialized by common methods. In this sense, PA rewiring only reorganizes connections, while preserving the magnitude and distribution of the weights. We show through an extensive statistical analysis in image classification that performance is improved in most cases, both during training and testing, when using both simple and complex architectures and learning schedules. Our results show that, aside from the magnitude, the organization of the weights is also relevant for better initialization of deep ANNs.
翻译:深层次的学习文献不断以新的结构和培训技术更新。然而,最近的研究忽略了权重初始化,尽管对随机权重有一些令人感兴趣的发现。另一方面,最近的工作正在接近网络科学,以了解培训后人工神经网络的结构和动态。因此,在这项工作中,我们分析神经元在随机初始化网络中的中心位置。我们表明,神经神经力差异较高可能会降低性能,而神经力差异较低则通常会改善。然后,根据优等附加(PA)规则,提出一种新的神经连接方法,以其强度为基础,大大缩小以通用方法初始化的层的强度差异。从这个意义上说,巴勒斯坦权力机构只重新组合连接,同时保持重量的规模和分布。我们在图像分类方面进行广泛的统计分析后显示,在大多数情况下,在培训和测试期间,在使用简单和复杂的结构以及学习时间表时,性能都有所改善。我们的结果显示,除了规模外,重力的组织结构对于更好地初始化深层ANN值也具有相关性。