Abstract

To reduce random access memory (RAM) requirements and to increase speed of recognition algorithms we consider a weight discretization problem for trained neural networks. We show that an exponential discretization is preferable to a linear discretization since it allows one to achieve the same accuracy when the number of bits is 1 or 2 less. The quality of the neural network VGG-16 is already satisfactory (top5 accuracy 69%) in the case of 3 bit exponential discretization. The ResNet50 neural network shows top5 accuracy 84% at 4 bits. Other neural networks perform fairly well at 5 bits (top5 accuracies of Xception, Inception-v3, and MobileNet-v2 top5 were 87%, 90%, and 77%, respectively). At less number of bits, the accuracy decreases rapidly.

中文翻译：

---

预训练神经网络中神经网络连接权重的指数离散化

摘要

为了减少随机存取存储器（RAM）的要求并提高识别算法的速度，我们考虑了经过训练的神经网络的权重离散化问题。我们表明，指数离散比线性离散更可取，因为当位数减少1或2时，它允许一个实现相同的精度。在3位指数离散化的情况下，神经网络VGG-16的质量已经令人满意（top5精度为69％）。ResNet50神经网络在4位时显示top5精度为84％。其他神经网络在5位上表现相当不错（Xception，Inception-v3和MobileNet-v2 top5的top5精度分别为87％，90％和77％）。位数较少时，精度会迅速下降。