ID 原文 译文
26005 随着测试的进行，不断收集测试数据，动态更新测试类型和测试向量的测试故障率，同步调整测试类型以及测试向量的加载顺序。 With the test progressed, the test data was collected continuously, the test failure rate of test type and vector were updated dynamically, and their loading order was adjusted synchronously．
26006 实验表明，使用动态调整后的测试流程可以更早的发现故障电路，显著减少故障电路的测试时间，提高测试效率。 The experimental results showed that the proposed method could significantly reduce test time and improve test efficiency．
26007 本算法是完全基于软件的，不需要增加硬件开销，可以相容于传统的集成电路测试流程。 Furthermore, the proposed algorithm is completely based on software, no additional hardware overhead, and canbe compatible with the traditional integrated circuit testing process．
26008 动态视觉传感器(Dynamic Vision Sensor，DVS)利用事件驱动原理实现运动目标的快速提取，具有低延迟、低存储空间和高动态范围等优势。 Dynamic vision sensor (DVS) shows significant advantages on low computational latency，low memory usage and high dynamic range by utilizing the event-driven principle to extract features from moving objects.
26009 目前研究表明，基于 DVS 的神经网络在目标检测等领域具有明显的速度优势。 Current research shows that DVS-based neural networks improve object detection speed obviously．
26010 但是，这类神经网络在训练时所需要的样本集主要依赖 DVS 相机产生，缺少高效的样本集生成方法，这制约了这类神经网络的应用与发展。 However, the sample sets required by such neural networks mainly rely on specific DVS cameras while lacking efficient generation methods for the sample sets． It limits the application and development of those neural networks．
26011 本文根据 DVS 原理，提出了一种基于帧图像的 DVS 建模以及样本集建模方法．该方法设定每个像素单元独立工作，经过动态差分和逻辑判断后输出触发的地址-事件数据，这些数据通过编码和归一化生成神经网络训练时所需要的样本集。 According to the principle of DVS, this paper presents a DVS sample set modeling method based on frame images, in which the sample set can be generated by encoding and normalizing the address-event( AE) data after being trigged by dynamic differential comparisons and logical judgments．
26012 通过对 MNIST 和 CIFAＲ-10 样本集建模的实验结果表明，该建模方法效果与 DVS 相机基本一致; The experimental results for modeling the MNIST and CIFAＲ-10 sample sets show that，the sample set modeled by the proposed method is basically matched with the real DVS cameras．
26013 与基于帧图像的存储方式相比，该样本集可以明显减少存储空间。 Compared with traditional frame image sample sets, this method can significantly reduce the memory usage．
26014 该方法所生成样本集已经通过卷积神经网络训练和测试验证。 The sample set generated by the proposed modeling method has also been verified by training and testing a typical convolutional neural network．