Purin：受生物学启发的突触效能调制机制提升 CNN 准确率
Purin: A Biology-inspired Mechanism for Artificial Neural Networks
arXiv 上新出的 Purin 机制，给 AlexNet、VGG11 这些老 CNN 加了突触效能调制，三个模型准确率都涨了，搞 CV 的可以看看。
论文提出 Purin，一种兼容常规 ANN 的生物学启发机制，将突触效能调制引入卷积神经网络。Purin 用基于时间间隔的抽象来表示神经活动，无需离散时间步即可引入短期和长期突触效能变化。机制包含一个表示临时突触效能变化的有界因子，以及输入侧和输出侧两个权重矩阵，二者通过反向传播更新。实验显示，在排除混淆因素后，Purin 使 AlexNet、VGG11 和 GoogLeNet 三个模型在所有评测数据集上的分类准确率均有提升。
Purin: A Biology-inspired Mechanism for Artificial Neural Networks
Artificial neural networks (ANNs) usually represent neural transmission with fixed trainable weights during a training batch, which omits short-term changes in synaptic efficacy. In addition, the discrete time-step simulation requires additional temporal processing that many conventional ANN architectures do not use. To overcome these challenges, we propose Purin, a biology-inspired and ANN-compatible mechanism, that introduces synaptic efficacy modulation into conventional convolutional neural networks. Purin uses a time-interval-based abstraction for neural activities, which allows Purin to introduce short- and long-term synaptic efficacy changes without using discrete time-steps. Purin introduces a bounded factor to represent temporary synaptic efficacy changes, together with two weight matrices that represent input-side and output-side efficacy. The weight matrices are updated by backpropagation and interpreted as the long-term synaptic efficacy changes. Experimental results show that after removing the confounding factors in the AlexNet, VGG11, and GoogLeNet architectures, Purin improves the classification accuracies in all three models across the evaluated datasets.
