ID 原文 译文
46736 解决了具有分布式、规模大、接入信号多、并行传输等特征的现代复杂通信系统的日益迫切的通信安全问题， It solved the increasingly urgent communication security issues of modern complex distributed and large scale communication system with many access signals and parallel transmission.
46737 并以永磁同步电机混沌模型，进行了仿真和验证。 In addition, with permanent magnet synchronous motor chaos model, simulation and validation were conducted.
46738 仿真结果表明，所提方法具有良好的应用前景，适用于现代通信系统。 The experimental results show that the method has good application prospect, and is suitable for modern communication system.
46739 针对深度卷积神经网络中 maxout 单元非最大特征无法传递、特征图像子空间池化表达能力不足的局限性， The maxout units have the problem of not delivering non-max features, resulting in the insufficient of pooling operation over a subspace that is composed of several linear feature mappings, when they are applied in deep convolutional neural networks.
46740 提出混合 maxout (mixout, mixed maxout)单元。 The mixed maxout (mixout) units were proposed to deal with this constrain.
46741 首先，计算相同输入在不同卷积变换下所形成的特征图像子空间的指数概率分布； Firstly, the exponential probability of the feature mappings getting from different linear transformations was computed.
46742 其次，根据概率分布计算特征图像子空间的期望； Then, the averaging of a subspace of different feature mappings by the exponential probability was computed.
46743 最后，利用伯努利分布对子空间的最大值与期望值加权，均衡单元模型。 Finally, the output was randomly sampled from the max feature and the mean value by the Bernoulli distribution, leading to the better utilizing of model averaging ability of dropout.
46744 分别构建基于 mixout 单元的简单模型和网中网模型进行实验， The simple models and network in network models was built to evaluate the perforate-mance of mixout units.
46745 结果表明 mixout单元模型性能较好。 The results show that mixout units based models have better performance.