Symmetry-structured convolutional neural networks
Symmetry-structured convolutional neural networks
复制标题
DOI：
10.1007/s00521-022-08168-3
复制
发表时间：
2022-03
影响因子：
6
通讯作者：
K. D. G. Maduranga;Vasily Zadorozhnyy;Qiang Ye
中科院分区：
文献类型：
--
作者：
K. D. G. Maduranga;Vasily Zadorozhnyy;Qiang Ye
我们考虑具有在空间维度上对称的2D结构特征的卷积神经网络（CNN）。这样的网络出现在建模成对关系的顺序推荐问题，以及二级结构推理问题的RNA和蛋白质序列。我们开发了一种CNN架构，可以生成并保留网络卷积层中的对称结构。我们提出了卷积核的参数化，这些参数化产生更新规则，以在整个训练过程中保持对称性。我们将这种架构应用于顺序推荐问题，RNA二级结构推理问题和蛋白质接触图预测问题，表明对称结构网络使用较少的机器参数产生改进的结果。
We consider convolutional neural networks (CNNs) with 2D structured features that are symmetric in the spatial dimensions. Such networks arise in modeling pairwise relationships for a sequential recommendation problem, as well as secondary structure inference problems of RNA and protein sequences. We develop a CNN architecture that generates and preserves the symmetry structure in the network’s convolutional layers. We present parameterizations for the convolutional kernels that produce update rules to maintain symmetry throughout the training. We apply this architecture to the sequential recommendation problem, the RNA secondary structure inference problem, and the protein contact map prediction problem, showing that the symmetric structured networks produce improved results using fewer numbers of machine parameters.