arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.03443cs.NEcs.AI
收藏

群剪:将类脑计算设计扩展到大型神经网络

Group Scissor: Scaling Neuromorphic Computing Design to Large Neural Networks

University of Pittsburgh(匹兹堡大学)

Yandan Wang, Wei Wen, Beiye Liu, Donald Chiarulli, Hai Li

摘要:

突触交叉是类脑计算系统的基本结构。然而,交叉开关的有限尺寸和严重的路由拥塞阻碍了大型神经网络的NCS实现。在本文中,我们提出了一个两步的框架(即,组群)规模的NCS设计大神经网络。第一步是秩裁剪,它将低秩近似集成到训练中以减少总交叉杆面积。第二步是组连接删除,从结构上修剪连接以减少交叉开关之间的路由拥塞。在MNIST数据库上的LeNet和CIFAR-10数据库上的ConvNet的卷积神经网络上进行测试,实验结果表明,网络控制系统设计中交叉开关面积和布线面积显著减少。在没有精度损失的情况下,秩裁剪将LeNet和ConvNet的NCS设计中的总交叉杆面积分别减少到13.62%和51.81%。在秩裁剪之后,组连接删除进一步将LeNet和ConvNet的路由区域分别减少到8.1%和52.06%。

英文摘要:

Synapse crossbar is an elementary structure in Neuromorphic Computing Systems (NCS). However, the limited size of crossbars and heavy routing congestion impedes the NCS implementations of big neural networks. In this paper, we propose a two-step framework (namely, group scissor) to scale NCS designs to big neural networks. The first step is rank clipping, which integrates low-rank approximation into the training to reduce total crossbar area. The second step is group connection deletion, which structurally prunes connections to reduce routing congestion between crossbars. Tested on convolutional neural networks of LeNet on MNIST database and ConvNet on CIFAR-10 database, our experiments show significant reduction of crossbar area and routing area in NCS designs. Without accuracy loss, rank clipping reduces total crossbar area to 13.62\% and 51.81\% in the NCS designs of LeNet and ConvNet, respectively. Following rank clipping, group connection deletion further reduces the routing area of LeNet and ConvNet to 8.1\% and 52.06\%, respectively.

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。

↑