高级检索
    方荣强, 王晶, 姚治成, 刘畅, 张伟功. 多层神经网络算法的计算特征建模方法[J]. 计算机研究与发展, 2019, 56(6): 1170-1181. DOI: 10.7544/issn1000-1239.2019.20190111
    引用本文: 方荣强, 王晶, 姚治成, 刘畅, 张伟功. 多层神经网络算法的计算特征建模方法[J]. 计算机研究与发展, 2019, 56(6): 1170-1181. DOI: 10.7544/issn1000-1239.2019.20190111
    Fang Rongqiang, Wang Jing, Yao Zhicheng, Liu Chang, Zhang Weigong. Modeling Computational Feature of Multi-Layer Neural Network[J]. Journal of Computer Research and Development, 2019, 56(6): 1170-1181. DOI: 10.7544/issn1000-1239.2019.20190111
    Citation: Fang Rongqiang, Wang Jing, Yao Zhicheng, Liu Chang, Zhang Weigong. Modeling Computational Feature of Multi-Layer Neural Network[J]. Journal of Computer Research and Development, 2019, 56(6): 1170-1181. DOI: 10.7544/issn1000-1239.2019.20190111

    多层神经网络算法的计算特征建模方法

    Modeling Computational Feature of Multi-Layer Neural Network

    • 摘要: 随着深度学习算法在语音和图像等领域中的成功运用,能够有效提取目标特征并做出最优决策的神经网络再次得到了广泛的关注.然而随着数据量的增加和识别精度需求的提升,神经网络模型的复杂度不断提高,因此采用面向特定领域的专用硬件加速器是高效运行神经网络的有效途径.然而如何根据网络规模设计高能效的加速器,以及基于有限硬件资源如何提高网络性能并最大化资源利用率是当今体系结构领域研究的重要问题.为此,提出基于计算特征的神经网络分析和优化方法,基于“层”的粒度解析典型神经网络模型并提取模型通用表达,根据通用表达式和基本操作属性提取模型运算量和存储空间需求等特征.提出了基于最大值更替的运行调度算法,利用所提取的特征分析结果对神经网络在特定硬件资源下的运行调度方案进行优化.实验结果显示:所提方法能够有效分析对比网络特征,并指导所设计调度算法实现性能和系统资源利用率的提升.

       

      Abstract: Deep neural networks (DNNs) have become increasingly popular as machine learning technique in applications, due to their ability to achieve high accuracy for tasks such as speech/image recognition. However, with the rapid growth on the scale of data and precision of recognition, the topology of neural network is becoming more and more complicated. Thus, how to design the energy-efficiency and programmability, neural or deep learning accelerator plays an essential role in next generation computer. In this paper, we propose a layer granularity analysis method, which could extract computation operations and memory requirement features through general expression and basic operation attributions. We also propose a max value replacement schedule strategy, which schedules the computation hardware resource based on the network feature we extract. Evaluation results show our method can increase computational efficiency and lead to a higher resource utilization.

       

    /

    返回文章
    返回