arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.09533cs.NEcs.LGstat.ML
收藏

一种自适应局部连通神经元模型:聚焦神经元

An Adaptive Locally Connected Neuron Model: Focusing Neuron

Isik University(伊希克大学)

F. Boray Tek

摘要:

本文提出了一种新的人工神经元模型,能够在输入的拓扑域中学习其感受野。该模型提供了自适应和可微的局部连通性(可塑性)适用于任何领域。它不需要其他工具比反向传播算法来学习它的参数控制的感受野的位置和孔径。这项研究探讨了这种能力是否会使神经元专注于信息输入,并产生比完全连接的神经元更大的优势。实验包括将一个或两个隐藏层的神经元网络集中在合成的和已知的图像识别数据集上的测试。结果表明,聚焦神经元可以将它们的感受野移向更多信息的输入。在简单的双隐层网络中,聚焦层在2D空间数据集的分类中优于密集层。此外,即使当70个$\%$的权重被修剪时,聚焦网络也比密集网络表现得更好。对卷积网络的测试表明,使用聚焦层而不是密集层来分类卷积特征在某些数据集中可能会更好。

英文摘要:

This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters which control the receptive field locations and apertures. This research explores whether this ability makes the neuron focus on informative inputs and yields any advantage over fully connected neurons. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic and well-known image recognition data sets. The results demonstrated that the focusing neurons can move their receptive fields towards more informative inputs. In the simple two-hidden layer networks, the focusing layers outperformed the dense layers in the classification of the 2D spatial data sets. Moreover, the focusing networks performed better than the dense networks even when 70$\%$ of the weights were pruned. The tests on convolutional networks revealed that using focusing layers instead of dense layers for the classification of convolutional features may work better in some data sets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑