programme_III

matlab 输入输出小例子 输入输出小例子(matlab input/output small example)

这个程序是计算一定年分的闰月，具有高效的计算，方便，简介，是用matlab编程的，(This program is calculated Year' s leap month, efficient computing, convenient, Profile, matlab programming,)

Karge Thompson算法的MATLAB源程序。(The algorithm of Karge Thompson is a heuristic algorithm that allows to obtain, given a specific group of jobs to be produced, the best sequence in terms of time setup. )

grab_cut,graph gut的进阶版，运用了lazy snapping(There are advanced segmentation algorithms in the literature which extends the concepts of graph cuts. Most prominent of them are Graph cuts and Lazy Snapping. Lazy napping is an interactive image cut out tool. Lazy Snapping separates coarse and fine scale processing, making object specification and detailed adjustment easy.)

空间目标识别，采用PM算法，这是第二能量熵的matlab代码，该函数用来计算任意函数的一阶偏导数(数值方法),构成不同频率的调制信号，高斯白噪声的生成程序，一种基于多文档得图像合并技术。

AR自回归模型，主要介绍时间序列分析中重要的一个模型。(AR autoregression model, time series analysis introduces an important model.)

MATLAB不提供现成指数拟合函数，一方面由于但可以轻松通过多项式拟合转化而来，但是使用上还是不如有一个函数方便，所以特写这样一样简单实用的函数(MATLAB does not provide ready-exponential fit function, by hand because it can be easily transformed a polynomial fit, but still not as good as there is easy to use a function, it is as simple close-up of such useful functions)

说明：  深度神经网络在函数近似中表现优越，然而需要从头开始训练。另一方面，贝叶斯方法，像高斯过程（GPs），可以利用利用先验知识在测试阶段进行快速推理。然而，高斯过程的计算量很大，也很难设计出合适的先验。本篇论文中我们提出了一种神经模型，条件神经过程（CNPs），可以结合这两者的优点。CNPs受灵活的随机过程的启发，比如GPs，但是结构是神经网络，并且通过梯度下降训练。CNPs通过很少的数据训练后就可以进行准确的预测，然后扩展到复杂函数和大数据集。我们证明了这个方法在一些典型的机器学习任务上面的的表现和功能，比如回归，分类和图像补全(Deep neural networks perform well in function approximation, but they need to be trained from scratch. On the other hand, Bayesian methods, such as Gauss Process (GPs), can make use of prior knowledge to conduct rapid reasoning in the testing stage. However, the calculation of Gauss process is very heavy, and it is difficult to design a suitable priori. In this paper, we propose a neural model, conditional neural processes (CNPs), which can combine the advantages of both. CNPs are inspired by flexible stochastic processes, such as GPs, but are structured as neural networks and trained by gradient descent. CNPs can predict accurately with very little data training, and then extend to complex functions and large data sets. We demonstrate the performance and functions of this method on some typical machine learning tasks, such as regression, classification and image completion.)

B-样条是样条曲线一种特殊的表示形式。它是B-样条基曲线的

说明：  利用特征提取和分类的方法,假设输入值为{大,圆,光滑}为水果的三个特征值,来代表三种不同的水果,识别苹果\梨\香蕉\桔子\菠萝水果类别. (The use of feature extraction and classification methods, assuming that the import value was (large, round, smooth fruit) for the three characteristics of value, to represent three different types of fruit, to identify Apple \ pear \ banana \ orange \ pineapple fruit category.)