论文标题
预先训练的神经网络中神经网络连接权重的指数离散化
Exponential discretization of weights of neural network connections in pre-trained neural networks
论文作者
论文摘要
为了减少随机访问记忆（RAM）要求并提高识别算法的速度，我们考虑了训练有素的神经网络的权重离散问题。我们表明，指数离散化比线性离散化更可取，因为它允许当位数少于1或2时，可以达到相同的精度。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位时显示出TOP5精度为84％。其他神经网络在5位（Xpection，Inception-V3和Mobilenet-V2 Top5的Top5精度分别为87％，90％和77％）的其他神经网络的表现相当出色。在较少的位数下，准确性迅速降低。
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.
