搜索资源列表
Inverse_tutorials
- Inverse problems example, this package uses different regularization algorithms.
l_curve
- 反演问题中正则化参数阿尔法的l-curve选取方法，用于画出l-curve，选取曲率最大的点。-Inverse problem regularization parameter alpha l-curve selection method used to draw l-curve, the point of maximum curvature.
l1_regularized-LSP
- 压缩感知信号重构算法，基于L1正则化的重构算法，可以学习学习。-Compressed sensing signal reconstruction based on L1 regularization reconstruction algorithms ，solve l1-regularized least squares problems
CH4_ex2
- 地球物理反演中的一个例子，用于比较各阶Tiknohv正则化的不同-Geophysical Inversion one example for each order Tiknohv compare different regularization
Nonlinear_Diffusion_v1.2
- 代码支持齐次线性和非线性（总变差和边缘增强流动）的任意尺寸领域各向同性扩散（标量/灰度图像，彩色图像和矩阵向量/结构张量）。添加剂算子分裂（AOS）以及高斯正则化的实现加速计算。-The code supports homogeneous and linear and nonlinear (Total Variation and Edge Enhancing flow) isotropic diffusion of arbitrary dimensioned fields(scalar~gray
CoGEnT_v1
- Forward - Backward Greedy Algorithms for Atomic Norm Regularization-Forward- Backward Greedy Algorithms for Atomic Norm Regularization
EmissionTomography-PETaSPECT
- This file is for regularization and emission tomography
LowPatchRank_regularization
- 对于带噪声的周期性纹理图像,提出一种基于二维秩约束的混合正则化去噪方法。该方法结合了全变分去噪理论和方法，并且利用该类图像低块秩的特性，对图像进行了低块秩约束。通过和全变分去噪方法比较可知，对于周期性纹理图像，混合正则化方法能有效地分离出噪声，并且能让图像很好地保持边缘。即使非严格的周期性纹理，该方法依然有很好的去噪效果。-For periodic texture images with noise, a new method based on two dimensional rank cons
ex4
- 加入正则项的线性回归，并对不同的正则项测试其拟合程度-Join regularization term linear regression, and different regular tests of their fitting degree
dehaze_code
- Efficient Image Dehazing with Boundary Constraint and Contextual Regularization
22222
- 学生档案信息进行管理,具有着手工管理所无法比拟的优点.例如:检索迅速、查找方便、可靠性高、存储量大、保密性好、寿命长、成本低等。这些优点能够极大地提高学生档案管理的效率,也是教育单位的科学化、正规化管理与世界接轨的重要条件。-Student archives information management, with manual management incomparable advantages, such as: the rapid retri , search convenient, hi
Image-deblurring-
- 一份关于用正则化去除图像模糊的资料，内含代码以及说明，并附上了仿真结果图-A report on the Regularization blur removal image data containing codes and descr iptions, along with the simulation results of FIG.
Tikhonov-for-inverse-problem
- 《不适定问题的正则化方法及应用》pp.6例题1.2的Tikhonov正则化方法及迭代Tikhonov正则化方法程序包。-Tikhonov regularization method and iterative Tikhonov regularization method package for the book regularization method and applications of ill-posed problems pp.6 example 1.2.
Singularvaluedecomposition
- 广义奇异值分解程序，常应用于数据处理，例如信号处理-The generalized singular value decomposition (GSVD) is a matrix decomposition more general than the singular value decomposition. It is used to study the conditioning and regularization of linear systems with respect to quad
ARKFCM_demo
- 脑图像分割基于自适应正则化的基于核的FCM分割，希望对大家有用-Brain Image Segmentation Based on Adaptive Regularization Based on Kernel FCM segmentation, we hope to be useful
CS_ROMP
- 压缩感知重构算法之正则化正交匹配追踪(ROMP)算法的MATLAB函数代码-Compressed sensing reconstruction algorithm of regularization orthogonal matching pursuit (ROMP) algorithm MATLAB code for the function
cnn_tutorial.pdf
- 本文档讨论和实现了卷积神经网络， 并且进行了延伸。非常重要的资料，对于深度学习有很重要的借鉴意义。 -This document discusses the derivation and implementation of convolutional neural networks (CNNs), followed by a few straightforward extensions. Convolutional neural networks involve many more connec
meridian
- image denoising by method proposed in signal processing paper(Salt-and-Pepper Noise Removal by Median-Type Noise Detectors and Detail-Preserving Regularization).
AIRtools(1)
- the regularization for algorithms
bp2
- 采用贝叶斯正则化算法提高 BP 网络的推广能力。 在本例中，我们采用两种训练方法，即 L-M 优化算法（trainlm）和贝叶斯正则化算法（trainbr），用以训练 BP 网络，使其能够拟合某一附加有白噪声的正弦样本数据。-Bayesian regularization algorithm to improve the generalization ability of BP network. In this example, we use two training methods, na