This work shows how using reduced precision data in Convolutional Neural Networks (CNNs) affects network accuracy during classification. Unlike similar studies, this study considers networks where each layer may use different precision data. The key result of this study is that the tolerance of CNNs to reduced precision data not only varies across networks, a well established observation, but also within networks. Tuning precision per layer is appealing as it could enable energy and performance improvements. The trends of error tolerance across layers are studied and a method for finding a low precision configuration for a network while maintaining high accuracy is presented. A diverse set of CNNs is analyzed showing that compared to a conventional implementation using a 32-bit floating-point representation for all layers, and with less than 1% loss in relative accuracy, the data footprint required by these networks can be reduced by an average of 74% and up to 92%.

该研究考虑了使用不同精度数据的卷积神经网络对其分类准确性的影响，发现误差容限不仅在不同网络之间有差异，而且在网络内部也有变化；进一步提出了一种方法，可以找到网络的低精度配置，同时保持高准确性。研究表明，相对于在所有层中使用32位浮点表示的传统实现，数据足迹可以平均减少74％，最高可降至92％，而相对准确性损失不到1％。

深度神经网络有界内存的降低精度策略