这是一个压缩传感方面的Gradient Projection for Sparse Reconstruction 工具包。

2、梯度函数——gradient [Fx,Fy]=gradient(F)%返回矩阵F的数值梯度，Fx相当于dF/dx，为x方向的差分值。Fy相当于dF/dy，为y方向的差分值。 [Fx,Fy]=gradient(F,H)%当H为数量时，使用H为各方向的点间隔。 [Fx,Fy]=gradient(F,Hx,Hy)%当F为二维时，使用Hx和Hy指定点间距。Hx和Hy可以为数量和向量，如果Hx和Hy为向量，则它们的长度必须和F的长度匹配。 [Fx,Fy,Fz]=gradient(F)%返回三维的梯度。 ……

该文档对比了现有的字符识别的方法，本文将CNN应用于字符识别中，通过实验验证了其性能。

上传的是用C语言实现的共轭梯度法的程序，注释不是特别多，需要有基础才容易读懂，输入可以自由更改，对于计算方法课程可以直接做源程序交上去

使用随机梯度下降法解决无约束优化问题。

Gradient Boosting Decision Tree

fmin_adam：亚当随机梯度下降优化算法的Matlab实现

Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradientbased learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of two dimensional (2-D) shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation, recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN’s), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank check is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal checks. It is deployed commercially and reads several million checks per day.

综合梯度 这是的pytorch实现。 原始的tensorflow版本可以在找到。 致谢 要求 python-3.5.2 pytorch-0.4.1 的OpenCVPython的 待办事项清单 添加更多功能作为原始代码。 微调结果，使它们接近原始纸张。 指示 强烈建议使用GPU加速计算。 如果使用CPU，我建议选择一些小型网络，例如resnet18 。 您还需要将图像放在examples/ 。 支持的网络列表（当然，您可以自己添加任何网络） 起始 网路18 resnet152 vgg19 运行代码 python main.py --cuda --model-type= ' inception ' --img= ' 01.jpg ' 结果 结果与原始论文略有不同，它可能存在一些错误或需要进行一些调整。 我会不断更新，欢迎任何贡献！ 盗梦空间v3 ResNet-18 ResNe

using Gaussian and gradient magnitude for image processing segmentation.