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 2102.00227cs.LGcs.CVcs.NE
收藏

NL-CNN:一种基于非线性卷积的资源受限深度学习模型

NL-CNN: A Resources-Constrained Deep Learning Model based on Nonlinear Convolution

Polytechnic University of Bucharest(布加勒斯特理工大学)

Radu Dogaru, Ioana Dogaru

摘要:

提出了一种新的卷积神经网络模型,简称NL-CNN,其中非线性卷积在卷积+非线性层的级联中仿真。其实施代码和一些经过训练的模型已公开提供。提供了几个广为人知的数据集的性能评估,显示了几个相关的特征:i)对于小/中等输入图像尺寸,所提出的网络给出了非常好的测试精度,给出了低的实现复杂度和模型尺寸; ii)与其他广为人知的资源约束模型相比,例如,与MobileNetv 2相比,它提供了更好的准确性,训练时间减少了几倍,参数减少了多达十倍(模型占用的内存); iii)具有一组相关的超参数,由于其特定的快速训练,可以轻松快速地进行调整。所有这些特征使得NL-CNN适用于物联网,智能传感,生物医学便携式仪器和其他必须在能量受限环境中部署人工智能的应用。

英文摘要:

A novel convolution neural network model, abbreviated NL-CNN is proposed, where nonlinear convolution is emulated in a cascade of convolution + nonlinearity layers. The code for its implementation and some trained models are made publicly available. Performance evaluation for several widely known datasets is provided, showing several relevant features: i) for small / medium input image sizes the proposed network gives very good testing accuracy, given a low implementation complexity and model size; ii) compares favorably with other widely known resources-constrained models, for instance in comparison to MobileNetv2 provides better accuracy with several times less training times and up to ten times less parameters (memory occupied by the model); iii) has a relevant set of hyper-parameters which can be easily and rapidly tuned due to the fast training specific to it. All these features make NL-CNN suitable for IoT, smart sensing, bio-medical portable instrumentation and other applications where artificial intelligence must be deployed in energy-constrained environments.

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。

↑