深度神经网络

  • 网络Deep Neural Network;DNN
深度神经网络深度神经网络
  1. 在该测试中,由阿里巴巴开发的深度神经网络模型得到82.44分,以微弱优势打败了人类参与者(82.304分)。

    The deep neural network model developed by Alibaba scored 82.44 on the test , narrowly beating the 82.304 achieved by human participants .

  2. 它凭借的是被称为“深度神经网络”的系统,同样的,该系统是由处理能力和数据存储能力驱动。

    it relied on what are known as " deep neural networks , " driven , once again , by processing power and data storage .

  3. 该团队开发了一种深度人工神经网络(ANN),它以现有的三体问题数据库和研究人员选出的精心制定的解决方案来进行训练。

    The team developed a deep artificial neural network ( ANN ) , trained on a database of existing three-body problems , plus a selection of solutions that have already been painstakingly worked out .

  4. 磨料水射流切割深度的神经网络模型

    Cutting Depth Model of Abrasive Waterjet Based on Neural Network Algorithm

  5. 桥墩局部冲刷深度模糊神经网络解的初步探讨

    Fuzzy neural network solution for bridge local scouring depth in the alluvial river bed

  6. AUV深度的模糊神经网络滑模控制

    Fuzzy neural network sliding-mode control of auto depth for AUV

  7. 混凝土碳化深度的人工神经网络分析与预测

    Analysis and Forecast for Carbonation Depth of Concrete by Artificial Neural Network

  8. 深度延迟人工神经网络判别水淹程度

    Application of depth - delay artifical neural network to discrimination of reservoir flooded degree

  9. 麻醉深度检测的神经网络模型的设计和训练。

    Designing and training of the ANN model .

  10. 煤层底板采动导水破坏深度计算的神经网络方法

    Prediction of the Failure Depth of Coal Seam Floor by Artificial Neural Network Method

  11. 漂石河床扩大基础桥墩局部冲刷深度的人工神经网络解

    The artificial neural network method used to calculate the depth of local scour of the expending base piers in the boulder riverbed

  12. 据说,深度学习和神经网络等技术会模仿人脑:它们会识别大量数据集中各种大的模式,以实现对图片的归类、识别声音和做出决定。

    Techniques such as deep learning and neural networks supposedly mimic the human brain : they spot broad patterns in enormous data sets in order to label images , recognise voices and make decisions .

  13. 二是利用深度延迟技术通过网络的训练与学习来确定剩余油饱和度的深度延迟人工神经网络法;

    The second , called a depth delay artificial neural network ( DDNN ) model , is to use the depth delay technique to determine the remaining oil saturation through training and learning of the neural network ;