Purin：一种受生物学启发的神经网络机制
Purin: A Biology-inspired Mechanism for Artificial Neural Networks
浏览论文内容
中文总结 AI 辅助
提出受生物学启发的Purin机制，通过时间间隔抽象和有界因子引入短期与长期突触效能调制，无需离散时间步长，在AlexNet、VGG11和GoogLeNet上提升分类准确率。
中文摘要 AI 辅助
人工神经网络（ANNs）通常在训练批次内用固定的可训练权重来表示神经传递，这忽略了突触效能的短期变化。此外，离散时间步长的模拟需要额外的时序处理，而许多传统ANN架构并未使用。为克服这些挑战，我们提出Purin，一种受生物学启发且与ANN兼容的机制，将突触效能调制引入传统卷积神经网络。Purin采用基于时间间隔的神经活动抽象，使其无需使用离散时间步长即可引入短期和长期的突触效能变化。Purin引入一个有界因子来表示临时的突触效能变化，同时使用两个权重矩阵分别表示输入侧和输出侧的效能。权重矩阵通过反向传播更新，并被解释为长期的突触效能变化。实验结果表明，在去除AlexNet、VGG11和GoogLeNet架构中的混淆因素后，Purin在所有三个模型及所评估的数据集上均提高了分类准确率。
英文摘要
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.
发表机构
- University of Exeter（埃克塞特大学）
- University of Wisconsin - Parkside（威斯康星大学帕克赛德分校）
机构由 AI 辅助整理，请以论文原文为准。
