提高神经网络的可学习性：添加辅助轴以解开数据表示
Improving learnability of neural networks: adding supplementary axes to disentangle data representation
摘要：
过度参数化的深度神经网络已被证明能够以100个$\%$训练精度学习任意数据集。由于过度拟合和计算成本问题的风险，如果我们想获得更好的医学图像训练结果，我们就不能增加网络节点的数量。以前的深度学习研究表明，当向网络中添加一些具有补充信息的节点时，神经网络的训练能力会显着提高（对于相同的训练时期）。这几个信息节点允许网络通过生成分解的数据表示来学习难以学习的特征。本文分析了附加信息作为补充轴的串联对神经网络训练的影响。该分析是针对二维训练数据上具有校正线性单元（ReLU）的简单多层感知器（MLP）分类模型进行的。我们比较了有和没有串联的补充信息的网络，以支持我们的分析。与没有级联的模型相比，具有级联的模型显示出更鲁棒和准确的训练结果。我们还证实了我们的发现对于使用超声图像的更深卷积神经网络（CNN）和使用MNIST数据的条件生成对抗网络（cGAN）是有效的。
英文摘要：
Over-parameterized deep neural networks have proven to be able to learn an arbitrary dataset with 100$\%$ training accuracy. Because of a risk of overfitting and computational cost issues, we cannot afford to increase the number of network nodes if we want achieve better training results for medical images. Previous deep learning research shows that the training ability of a neural network improves dramatically (for the same epoch of training) when a few nodes with supplementary information are added to the network. These few informative nodes allow the network to learn features that are otherwise difficult to learn by generating a disentangled data representation. This paper analyzes how concatenation of additional information as supplementary axes affects the training of the neural networks. This analysis was conducted for a simple multilayer perceptron (MLP) classification model with a rectified linear unit (ReLU) on two-dimensional training data. We compared the networks with and without concatenation of supplementary information to support our analysis. The model with concatenation showed more robust and accurate training results compared to the model without concatenation. We also confirmed that our findings are valid for deeper convolutional neural networks (CNN) using ultrasound images and for a conditional generative adversarial network (cGAN) using the MNIST data.
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。
