arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.07674cs.LGcs.AI
收藏

高效稀疏人工神经网络

Efficient Sparse Artificial Neural Networks

Sharif University of Technology(谢里夫理工大学)

Seyed Majid Naji, Azra Abtahi, Farokh Marvasti

摘要:

作为人工神经网络(ANN)的灵感来源,大脑基于稀疏结构。这种稀疏的结构有助于大脑消耗更少的能量,学习更容易,更好地概括模式比任何其他ANN。在本文中,提出了两种进化方法,采用稀疏的ANN。在所提出的方法中,网络的稀疏结构以及其参数值在学习过程中进行训练和更新。仿真结果表明,这两种方法具有更好的精度和更快的收敛速度,而他们需要更少的训练样本相比,他们的稀疏和非稀疏的同行。此外,所提出的方法显着提高泛化能力,减少参数的数量。例如,通过利用我们提出的用于ImageNet数据集图像分类的方法对ResNet47网络进行稀疏化,使用的参数减少了40%,而与密集网络和稀疏网络相比,模型的前1精度分别提高了12%和5%。作为另一个例子,针对CIFAR10数据集提出的方法收敛到其最终结构的速度比其稀疏对应物快7倍,而最终精度提高了6%。

英文摘要:

The brain, as the source of inspiration for Artificial Neural Networks (ANN), is based on a sparse structure. This sparse structure helps the brain to consume less energy, learn easier and generalize patterns better than any other ANN. In this paper, two evolutionary methods for adopting sparsity to ANNs are proposed. In the proposed methods, the sparse structure of a network as well as the values of its parameters are trained and updated during the learning process. The simulation results show that these two methods have better accuracy and faster convergence while they need fewer training samples compared to their sparse and non-sparse counterparts. Furthermore, the proposed methods significantly improve the generalization power and reduce the number of parameters. For example, the sparsification of the ResNet47 network by exploiting our proposed methods for the image classification of ImageNet dataset uses 40 % fewer parameters while the top-1 accuracy of the model improves by 12% and 5% compared to the dense network and their sparse counterpart, respectively. As another example, the proposed methods for the CIFAR10 dataset converge to their final structure 7 times faster than its sparse counterpart, while the final accuracy increases by 6%.

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。

↑