极限学习机: 新趋势与新应用
… process may take several hours/days or even more time using BP-like gradient-based methods.
… Specifically, we have highlighted the new trends of multilayer learning with ELM; those …
… Specifically, we have highlighted the new trends of multilayer learning with ELM; those …
[PDF][PDF] 利用小波变换的高分辨率多光谱遥感图像多尺度分水岭分割
陈杰， 邓敏， 肖鹏峰， 杨敏华， 梅小明， 刘慧敏 - 遥感学报, 2021 - ygxb.ac.cn
为了减少仅用分水岭变换而导致的过分割问题,本文提出利用小波变换的多尺度处理方式用于
融合后多光谱QuickBird图像的分割.整个分割过程包括多尺度图像表示,图像分割,区域合并和结果…
融合后多光谱QuickBird图像的分割.整个分割过程包括多尺度图像表示,图像分割,区域合并和结果…
[PDF][PDF] 贴片电阻焊点内部空洞缺陷自适应检测
蔡念， 肖盟， 肖盼， 周帅， 邱宝军， 王晗 - 电子与信息学报, 2022 - jeit.ac.cn
… In this paper, an adaptive inspection method for void defects inside solder joints of chip
resistors is proposed by combining a Local Pre-Fitted (LPF) active contour model and circular …
resistors is proposed by combining a Local Pre-Fitted (LPF) active contour model and circular …
[HTML][HTML] 基于多模态时间序列建模的机器人安全监控
吴鸿敏， 张国英， 管贻生 - 哈尔滨工业大学学报, 2020 - hit.alljournals.cn
… process could also be implemented by discriminating anomalies by the gradient of log-likelihood
thresholding … 6 Log-likelihood and gradient-based log-likelihood of a testing task. The …
thresholding … 6 Log-likelihood and gradient-based log-likelihood of a testing task. The …
改良式杜鵑鳥演算法發展與應用
YHUA CIOU - 2016 - ir.lib.ncu.edu.tw
(中) 本文針對連續變數, 離散變數, 混和變數等最佳化問題, 以杜鵑鳥演算法(Cuckoo Search
Algorithm, CS) 為基礎, 提出改良式杜鵑鳥演算法(Modified cuckoo search, MCS). CS 演算法為…
Algorithm, CS) 為基礎, 提出改良式杜鵑鳥演算法(Modified cuckoo search, MCS). CS 演算法為…
[PDF][PDF] 基于快速残差插值和卷积神经网络的去马赛克算法
汤漫， 杨斌 - 南华大学学报(自然科学版), 2019 - nhqks.cnjournals.com
… plemented by the improved gradient-based fast residual interpolation method,and the color
… Color demosaicking by local directional interpolation and nonlocal adaptive thresholding[J]. …
… Color demosaicking by local directional interpolation and nonlocal adaptive thresholding[J]. …
光学神经网络及其应用
陈蓓， 张肇阳， 戴庭舸， 余辉， 王曰海… - Laser & Optoelectronics …, 2023 - opticsjournal.net
由于光传输具备高通量, 低延迟, 低能耗等优势, 光学神经网络有望应对目前人工智能技术发展中
所面临的能耗和计算效率的挑战, 成为近年来学术界和工业界的研究热点. 光学神经网络的目标…
所面临的能耗和计算效率的挑战, 成为近年来学术界和工业界的研究热点. 光学神经网络的目标…
利用捲積類神經網路定位複雜背景中的條碼
周子涵 - 2015 - tdr.lib.ntu.edu.tw
… The algorithm applied multilayer perceptron network to detect 1D barcode by using the
parameters of 2D Hough transform space. Some literature on local detection was also proposed. …
parameters of 2D Hough transform space. Some literature on local detection was also proposed. …
[HTML][HTML] 相位敏感光时域反射仪的信号处理方法综述
田曼伶， 刘东辉， 曹晓敏， 余贶琭 - Optics and Precision …, 2021 - opticsjournal.net
… This study summarizes the signal processing methods used to improve the signal-to-noise
ratio and vibration recognition rate of the system, including noise reduction algorithms, feature …
ratio and vibration recognition rate of the system, including noise reduction algorithms, feature …
基于三维卷积神经网络的肺结节探测与定位方法.
侯智超， 杨杨， 李晓琴 - Chinese Journal of Bioinformatics, 2022 - search.ebscohost.com
… Multilevel thresholding based segmen⁃ tation and feature extraction for pulmonary nodule
… Gradient⁃based learning applied to document recognition[J]. Proceedings of the IEEE,1998,…
… Gradient⁃based learning applied to document recognition[J]. Proceedings of the IEEE,1998,…