中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共8条，第1-8条

帮助

条数/页：排序方式：
	Understanding the acceleration phenomenon via high-resolution differential equations 期刊论文 OAI收割 MATHEMATICAL PROGRAMMING, 2022, 卷号: 195, 期号: 1-2, 页码: 79-148 作者: Shi, Bin; Du, Simon S.; Jordan, Michael, I; Su, Weijie J. \| 收藏 \| 浏览/下载：30/0 \| 提交时间：2023/02/07 Convex optimization First-order method Polyak's heavy ball method Nesterov's accelerated gradient methods Ordinary differential equation Lyapunov function Gradient minimization
	A Minibatch Proximal Stochastic Recursive Gradient Algorithm Using a Trust-Region-Like Scheme and Barzilai-Borwein Stepsizes 期刊论文 OAI收割 IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 卷号: 32, 期号: 10, 页码: 4627-4638 作者: Yu, Tengteng; Liu, Xin-Wei; Dai, Yu-Hong; Sun, Jie \| 收藏 \| 浏览/下载：20/0 \| 提交时间：2022/04/02 Convergence Convex functions Risk management Gradient methods Learning systems Sun Barzilai-Borwein (BB) method empirical risk minimization (ERM) proximal method stochastic gradient trust-region
	Stereoscopic Image Stitching via Disparity-Constrained Warping and Blending 期刊论文 OAI收割 IEEE TRANSACTIONS ON MULTIMEDIA, 2020, 卷号: 22, 期号: 3, 页码: 655-665 作者: Fan, Xiaoting; Lei, Jianjun; Fang, Yuming; Huang, Qingming; Ling, Nam \| 收藏 \| 浏览/下载：31/0 \| 提交时间：2020/12/10 Stereo image processing Distortion Two dimensional displays Visualization Minimization methods Shape Feature extraction Stereoscopic image image stitching disparity consistency multi-constraint warping seam-cutting and blending
	Generalized Latent Multi-View Subspace Clustering 期刊论文 OAI收割 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2020, 卷号: 42, 期号: 1, 页码: 86-99 作者: Zhang, Changqing; Fu, Huazhu; Hu, Qinghua; Cao, Xiaochun; Xie, Yuan \| 收藏 \| 浏览/下载：59/0 \| 提交时间：2020/03/30 Clustering methods Correlation Electronic mail Neural networks Task analysis Clustering algorithms Minimization Multi-view clustering subspace clustering latent representation neural networks
	Inexact proximal stochastic gradient method for convex composite optimization 期刊论文 OAI收割 COMPUTATIONAL OPTIMIZATION AND APPLICATIONS, 2017, 卷号: 68, 期号: 3, 页码: 579-618 作者: Wang, Xiao; Wang, Shuxiong; Zhang, Hongchao \| 收藏 \| 浏览/下载：39/0 \| 提交时间：2018/07/30 Convex composite optimization Empirical risk minimization Stochastic gradient Inexact methods Global convergence Complexity bound
	Frequency multiscale full-waveform velocity inversion 期刊论文 OAI收割 CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION, 2015, 卷号: 58, 期号: 1, 页码: 216-228 作者: Zhang WenSheng; Luo Jia; Teng JiWen \| 收藏 \| 浏览/下载：31/0 \| 提交时间：2021/01/14 ABSORBING BOUNDARY-CONDITIONS SEISMIC-REFLECTION DATA FINITE-FREQUENCY DIFFRACTION TOMOGRAPHY ELASTIC INVERSION NEWTON METHODS GAUSS-NEWTON DOMAIN MEDIA MINIMIZATION Acoustic wave equation Frequency multiscale Time domain Full-waveform inversion Velocity BFGS Marmousi model Finite-difference method MPI parallel
	A MLP-PNN neural network for CCD image super-resolution in wavelet packet domain (EI CONFERENCE) 会议论文 OAI收割 2008 International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM 2008, October 12, 2008 - October 14, 2008, Dalian, China Zhao X.; Fu D.; Zhai L. 收藏 \| 浏览/下载：68/0 \| 提交时间：2013/03/25 Image super-resolution methods process an input image sequence of a scene to obtain a still image with increased resolution. Classical approaches to this problem involve complex iterative minimization procedures typically with high computational costs. In this paper is proposed a novel algorithm for super-resolution that enables a substantial decrease in computer load. First decompose and reconstruct the image by wavelet packet. Before constructing the image use neural network in place of other rebuilding method to reconstruct the coefficients in the wavelet packet domain. Second probabilistic neural network architecture is used to perform a scattered-point interpolation of the image sequence data in the wavelet packet domain. The network kernel function is optimally determined for this problem by a MLP-PNN (Multi Layer Perceptron - Probabilistic Neural Network) trained on synthetic data. Network parameters dependent on the sequence noise level. This super-sampled image is spatially Altered to correct finite pixel size effects to yield the final high-resolution estimate. This method can decrease the calculation cost and get perfect PSNR. Results are presented showing the quality of the proposed method. 2008 IEEE.
	An increasing-angle property of the conjugate gradient method and the implementation of large-scale minimization algorithms with line searches 期刊论文 OAI收割 NUMERICAL LINEAR ALGEBRA WITH APPLICATIONS, 2003, 卷号: 10, 期号: 4, 页码: 323-334 作者: Dai, YH; Martinez, JM; Yuan, JY \| 收藏 \| 浏览/下载：13/0 \| 提交时间：2018/07/30 conjugate gradients unconstrained minimization truncated Newton methods truncated quasi-Newton methods large scale problems