arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2008.07387cs.LG
收藏

快速再训练的深度网络

Deep Networks with Fast Retraining

University of Windsor(温莎大学);Lakehead University(湖首大学);Vector Institute for Artificial Intelligence(矢量人工智能研究所)

Wandong Zhang, Yimin Yang, Jonathan Wu

摘要:

最近的工作[1]在深度卷积神经网络(DCNN)学习中利用了Moore-Penrose(MP)逆,其通过随机梯度下降(SGD)管道实现了比DCNN更好的泛化性能。然而,由于其对超参数的高度敏感性和对计算资源的严格要求,杨的工作在实践中并没有得到太多的普及。为了增强其适用性,本文提出了一种新的MP逆的快速再训练策略。在每个训练时期中,首先使用随机学习策略,该策略控制在反向传递中训练的卷积层的数量。然后,开发了一种基于MP逆的逐批学习策略,该策略使网络能够在不访问工业规模计算资源的情况下实现,以细化密集层参数。实验结果表明,快速再训练是一种统一的策略,可用于所有DCNN。与其他学习策略相比,该学习流水线对超参数具有鲁棒性,并且计算资源的需求显著降低。[1]Y. Yang,J. Wu,X. Feng,和A. Thangarajah,“Recomputation of dense layers for the perfor-238mance improvement of dcnn,”IEEE Trans. Pattern Anal.马赫内部:2019.

英文摘要:

Recent work [1] has utilized Moore-Penrose (MP) inverse in deep convolutional neural network (DCNN) learning, which achieves better generalization performance over the DCNN with a stochastic gradient descent (SGD) pipeline. However, Yang's work has not gained much popularity in practice due to its high sensitivity of hyper-parameters and stringent demands of computational resources. To enhance its applicability, this paper proposes a novel MP inverse-based fast retraining strategy. In each training epoch, a random learning strategy that controls the number of convolutional layers trained in the backward pass is first utilized. Then, an MP inverse-based batch-by-batch learning strategy, which enables the network to be implemented without access to industrial-scale computational resources, is developed to refine the dense layer parameters. Experimental results empirically demonstrate that fast retraining is a unified strategy that can be used for all DCNNs. Compared to other learning strategies, the proposed learning pipeline has robustness against the hyper-parameters, and the requirement of computational resources is significantly reduced. [1] Y. Yang, J. Wu, X. Feng, and A. Thangarajah, "Recomputation of dense layers for the perfor-238mance improvement of dcnn," IEEE Trans. Pattern Anal. Mach. Intell., 2019.

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。

↑