Fast integer approximations in convolutional neural networks using layer-by-layer training
Fast integer approximations in convolutional neural networks using layer-by-layer training
复制标题
使用逐层训练的卷积神经网络中的快速整数近似
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
D. Nikolaev
中科院分区：
文献类型：
--
作者：
D. Ilin;E. Limonova;V. Arlazarov;D. Nikolaev
本文探讨了神经网络的逐层训练方法，用于训练使用近似计算和/或低精度数据类型的神经网络。所提出的方法允许使用标准训练算法和工具来提高识别精度。同时，它允许使用快速处理的近似计算和紧凑的数据类型来加速神经网络计算。我们认为8位定点算法的图像识别问题的这种近似的例子。最后，我们显示出显着的精度增加所考虑的近似沿着与处理加速。
This paper explores method of layer-by-layer training for neural networks to train neural network, that use approximate calculations and/or low precision data types. Proposed method allows to improve recognition accuracy using standard training algorithms and tools. At the same time, it allows to speed up neural network calculations using fast-processed approximate calculations and compact data types. We consider 8-bit fixed-point arithmetic as the example of such approximation for image recognition problems. In the end, we show significant accuracy increase for considered approximation along with processing speedup.