机构

• 沈阳自动化研究所 [2]
• 物理研究所 [1]
• 长春光学精密机械与物... [1]
• 数学与系统科学研究院 [1]

采集方式

• OAI收割 [5]

内容类型

• 期刊论文 [4]
• 会议论文 [1]

发表日期

• 2020 [1]
• 2019 [2]
• 2011 [1]
• 2010 [1]

学科主题

筛选

浏览/检索结果: 共5条，第1-5条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择作者升序作者降序发表日期升序发表日期降序题名升序题名降序提交时间升序提交时间降序 Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units 期刊论文  OAI收割 COMMUNICATIONS IN COMPUTATIONAL PHYSICS, 2020, 卷号: 27, 期号: 2, 页码: 379-411 作者:  Li, Bo;  Tang, Shanshan;  Yu, Haijun   |  收藏  |  浏览/下载：28/0  |  提交时间：2020/05/24 Deep neural network  high dimensional approximation  sparse grids  rectified linear unit  rectified power unit  rectified quadratic unit   High-dimensional grouped folded concave penalized estimation via the LLA algorithm 期刊论文  OAI收割 Journal of the Korean Statistical Society, 2019, 卷号: 48, 期号: 1, 页码: 84-96 作者:  Guo X(郭骁);  Wang Y(王尧);  Zhang H(张海)   |  收藏  |  浏览/下载：43/0  |  提交时间：2019/02/24 Grouped variable selection  High-dimensional linear models  Folded concave penalty  Local linear approximation  Oracle estimator   Approximation for discrete Fourier transform and application in study of three-dimensional interacting electron gas 期刊论文  OAI收割 PHYSICAL REVIEW E, 2011, 卷号: 84, 期号: 1 Yan, XZ 收藏  |  浏览/下载：44/0  |  提交时间：2013/09/17 2-DIMENSIONAL HUBBARD-MODEL  D-P MODEL  GROUND-STATE  CONSERVING APPROXIMATION  CORRELATION ENERGY  HIGH DENSITY  SUPERCONDUCTIVITY  CRYSTALLIZATION  SYSTEMS   Image compression based on contourlet and no lists SPIHT (EI CONFERENCE) 会议论文  OAI收割 2010 International Conference on Computer, Mechatronics, Control and Electronic Engineering, CMCE 2010, August 24, 2010 - August 26, 2010, Changchun, China 作者:  Zhang S. 收藏  |  浏览/下载：74/0  |  提交时间：2013/03/25 The volume of raw image data captured by the high resolution camera is extremely huge. Thus the efficient image compression method should be used to decrease the bit rate. The image compression method based on wavelet is used more widely nowadays. However  two dimensional wavelet is only the tensor product of the one dimensional wavelet whose support region of basis function is extended from interval to square. Contourlet is an image multiscale geometric analysis tool  which could represent image sparsely and has strong capability of nonlinear approximation. The basis function of contourlet is multidirectional and anisotropic. Nevertheless  contourlet is redundant. So the non-redundant Wavelet Based Contourlet Transform (WBCT) is used in this paper. The SPIHT algorithm is very efficient way to coding the significant coefficients. And the improved no lists SPIHT is more easy to implemented by hardware. Image compression method based on the combination of both wavelet based contourlet transform and no lists SPIHT coding is proposed in the paper. Experiment shows that compared to wavelet based scheme the contourlet scheme can reserve the texture of the image. For barbara test image when coding at low bit rate the PSNR can improve about 0.2dB. 2010 IEEE.