ID 原文 译文
1873 包括基于不相交运算的 RM 逻辑错误率计算方法，及在错误率约束下，有利于面积优化的近似 FPRM 函数搜索方法等。 The proposed algorithm mainly consists of the method of the error rate computing of RM functions using disjointed products and the approach of the approximate FPRM functions search-ing for less area under the given error rate constraint.
1874 优化算法用MCNC (Microelectronics Center of North Carolina)电路进行测试。 The proposed algorithm is tested under MCNC(Microelectronics Centerof North Carolina)benchmarks.
1875 实验结果表明，提出的算法可以处理输入变量个数为199 个的大电路， The experimental results show that it can deal with the large function with 199 inputs.
1876 在平均错误率为 5.7% 下，平均电路面积减少 62.0% ， And by using the approximate computing technique, the average area can be reduced by 62. 0% with the average error rate of5. 7% .
1877 并在实现面积优化的同时有利于实现电路的动态功耗的优化且对电路时延影响不大。 The proposed approximate computing technique based algorithm is also beneficial for dynamic power saving and has little effect on the delay while optimizing the area of a circuit.
1878 当前，大部分农作物病害图像识别方法主要关注于精度而忽略了鲁棒性。 Most of current crop-disease recognition approaches mainly focus on improving the recognition accuracy onpublic datasets, while ignoring the recognition robustness.
1879 在面向实际环境时，由于噪声干扰和环境因素影响导致识别精度不高。 When dealing with real-world recognition problem, the actual rec-ognition accuracy of those approach are often unsatisfactory because of noise interference and environmental influence.
1880 为此提出了一种高阶残差和参数共享反馈的卷积神经网络模型以应用于实际环境农作物病害识别。 To address these issues, we propose a high-order residual and parameter-sharing feedback convolutional neural network(HORPSF)for crop-disease recognition.
1881 其中，高阶残差子网络为病害表观提供丰富细致的特征表达，以提高模型识别精度; The high-order residual subnetwork is helpful for improving the recognition accura-cy of crop disease.
1882 参数共享反馈子网络用来进一步抑制原深层特征中的背景噪声，以提高模型的鲁棒性。 The parameter-sharing feedback subnetwork can effectively depress the background noises and enhance the robustness of the model.