arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1808.08784cs.LGstat.ML
收藏

深度神经网络中的稀疏性-使用TensorQuant进行的实证研究

Sparsity in Deep Neural Networks - An Empirical Investigation with TensorQuant

Fraunhofer ITWM(弗劳恩霍夫工业数学研究所);TU Kaiserslautern(凯泽斯劳滕工业大学);Fraunhofer Center Machine Learning(弗劳恩霍夫机器学习中心)

Dominik Marek Loroch, Franz-Josef Pfreundt, Norbert Wehn, Janis Keuper

摘要:

深度学习正通过自动驾驶、智能传感器和增强现实等应用进入嵌入式世界。然而,深度神经网络的计算在能量、计算能力和存储器方面要求很高。已经研究了各种方法来减少必要的资源,其中之一是利用由于网络参数中的高冗余级别而在深度神经网络中发生的稀疏性。已经表明,稀疏性可以被具体地提升,并且所实现的稀疏性可以非常高。但在许多情况下,这些方法是在相当小的拓扑上进行评估的。尚不清楚结果是否转移到更深的拓扑结构上。在本文中,TensorQuant工具箱已经扩展到提供一个研究稀疏性的平台,特别是在更深层次的模型中。几个实际的相关拓扑结构不同的分类问题的大小进行了研究,以显示激活,权重和梯度的稀疏性的差异。

英文摘要:

Deep learning is finding its way into the embedded world with applications such as autonomous driving, smart sensors and aug- mented reality. However, the computation of deep neural networks is demanding in energy, compute power and memory. Various approaches have been investigated to reduce the necessary resources, one of which is to leverage the sparsity occurring in deep neural networks due to the high levels of redundancy in the network parameters. It has been shown that sparsity can be promoted specifically and the achieved sparsity can be very high. But in many cases the methods are evaluated on rather small topologies. It is not clear if the results transfer onto deeper topologies. In this paper, the TensorQuant toolbox has been extended to offer a platform to investigate sparsity, especially in deeper models. Several practical relevant topologies for varying classification problem sizes are investigated to show the differences in sparsity for activations, weights and gradients.

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。

↑