机构

• 长春光学精密机械与物... [2]
• 自动化研究所 [1]

采集方式

• OAI收割 [3]

内容类型

• 会议论文 [2]
• 期刊论文 [1]

发表日期

• 2021 [1]
• 2010 [1]
• 2006 [1]

学科主题

筛选

浏览/检索结果: 共3条，第1-3条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 Dynamically Optimizing Network Structure Based on Synaptic Pruning in the Brain 期刊论文  OAI收割 FRONTIERS IN SYSTEMS NEUROSCIENCE, 2021, 卷号: 15, 页码: 8 作者:  Zhao, Feifei;  Zeng, Yi   |  收藏  |  浏览/下载：34/0  |  提交时间：2021/08/15 synaptic pruning  developmental neural network  optimizing network structure  accelerating learning  compressing network   Prediction model of molten iron endpoint temperature in AOD furnace based on RBF neural network (EI CONFERENCE) 会议论文  OAI收割 2010 International Conference on Logistics Systems and Intelligent Management, ICLSIM 2010, January 9, 2010 - January 10, 2010, Harbin, China Ma H.-T.; You W.; Chen T. 收藏  |  浏览/下载：28/0  |  提交时间：2013/03/25 According to Jilin Ferroalloy Factory 10-ton AOD furnace actual smelting condition  analyzes the impact factor of AOD furnace molten iron endpoint temperature  by optimizing the neural network connection weights and structure  design prediction model of molten iron endpoint temperature based on RBF neural network  using LM algorithm and 50 furnaces actual production data to train the model  and predicts another 50 furnaces molten iron temperature  Result shows that prediction model of molten iron endpoint temperature based on RBF neural network has a high accuracy  when the error of endpoint temperature is 12 C  hit rate of temperature is 82.4%. 2010 IEEE.   Study on color model conversion for camera with neural network based on the combination between second general revolving combination design and genetic algorithm (EI CONFERENCE) 会议论文  OAI收割 ICO20: Illumination, Radiation, and Color Technologies, August 21, 2005 - August 26, 2005, Changchun, China 作者:  Li Z.;  Zhou F.;  Wang C.;  Li Z. 收藏  |  浏览/下载：36/0  |  提交时间：2013/03/25 Munsell color system is selected to establish the mutual conversion between RGB and L*a*b* color model for camera. The color luminance meter and CCD camera synchronously measure the same color card  XYZ value is gotten from the color luminance meter  the training error is 0.000748566  it can show that the method combining second general revolving combination design with genetic algorithm can optimize the hidden-layer structure of neural network. Using the data of testing set to test this network and calculating the color difference between forecast value and true value  the color picture captured from CCD camera is expressed for RGB value as the input of neural network  and the L*a*b* value converted from XYZ value is regarded as the real color value of target card  which the difference is not obvious comparing with forecast result  the maximum is 5.6357 NBS  namely the output of neural network. The neural network of two hidden-layers is considered  the minimum is 0.5311 NBS  so the second general revolving combination design is introduced into optimizing the structure of neural network  and the average of color difference is 3.1744 NBS.  which can carry optimization through unifying project design  data processing and the precision of regression equation. Their mathematics model of encoding space is gained  and the significance inspection shows the confidence degree of regression equation is 99%. The mathematics model is optimized by genetic algorithm  optimization solution is gotten  and function value of the goal is 0.0007168. The neural network of the optimization solution is trained