神经网络的安全使用
Safe Use of Neural Networks
AI总结：
针对现代通信系统中神经网络易受内部数值误差影响决策的问题，提出基于数字卷积码的算术错误检测方法，通过双路径生成奇偶校验值并结合泰勒级数近似保护激活函数，仿真验证其有效高效。
摘要：
现代通信系统中的神经网络易受内部数值误差影响，这类误差可能严重改变决策结果。这类结构由多个模块组成，每个模块通常包含加权运算和激活函数计算。安全使用的实现依托基于数字编码的方法，这类方法可检测网络处理步骤中的算术错误。每组运算会通过两种方式生成由编码决定的奇偶校验值：一组奇偶校验值从模块的输出中获取，另一组对应的奇偶校验值则直接从原始输入生成。用于保护激活函数的奇偶校验值涉及对激活函数的泰勒级数近似。由于数据集规模庞大，我们重点使用长数字卷积码，这类编码基于离散傅里叶变换（Discrete Fourier Transform）核，且有多种设计选项可供选择。数学程序仿真表明，我们的错误检测技术兼具有效性与高效性。
英文摘要：
Neural networks in modern communication systems can be susceptible to internal numerical errors that can drastically effect decision results. Such structures are composed of many sections each of which generally contain weighting operations and activation function evaluations. The safe use comes from methods employing number based codes that can detect arithmetic errors in the network's processing steps. Each set of operations generates parity values dictated by a code in two ways. One set of parities is obtained from a section's outputs while a second comparable set is developed directly from the original inputs. The parity values protecting the activation functions involve a Taylor series approximation to the activation functions. We focus on using long numerically based convolutional codes because of the large size of data sets. The codes are based on Discrete Fourier Transform kernels and there are many design options available. Mathematical program simulations show our error-detecting techniques are effective and efficient.
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。
