采用的是康力山等人确定的实验参数。 对于n个城市的旅行商问题，其参数如下： 初始温度：t0=280, 每一个温度下采用固定的迭代次数L=100n, 温度的衰

L-M算法。除了动量法(基于梯度下降的训练算法)外，学习率自适应调整策略是BP算法改进的另一种途径，它利用Levenberg-Marquardt优化方法，从而使得学习时间更短。其缺点是，对于复杂的问题，该方法需要很大的存储空间。 -L-M algorithm. In addition to momentum (based on the gradient descent algorithm for training), learning rate adaptive strategy is to improve the algorithm BP Another approach, which uses Levenberg-Marquardt optimization method, which makes learning time is even shorter. Its weakness is that the complex problems that the method requires a lot of storage space.

机器学习 的 课件 ppt格式 对于人工智能有兴趣的同学可以-Machine learning courseware ppt format for students who are interested in artificial intelligence can

matlab神经网络应用设计-Matlab neural network application design

bp神经网络,反向传播神经网络！感觉还不错的-bp neural networks, back-propagation neural network! Feeling pretty good

清华大学不确定规划教材中的模糊规划求解算法2-Tsinghua University, uncertainty in the planning of teaching materials fuzzy programming algorithm 2

这个程序是人工智能里字句归结的一个程序，它采用了线性归结策略和删除策略相结合的方法-the procedure is artificial intelligence Lane words attributed to the procedure, which uses the linear sum strategies and strategy to delete a combination of methods

Counterpropagation Network Vision 源码, 经典的CPN人工神经网络例子源码-Counterpropagation Network Vision Source, a classic example of artificial neural network CPN-source

本代码是人工智能中产生式的一个例子，功能是实现对有限动物特征识别的正向和反相推理。-the code is generated artificial intelligence-an example of that function is limited to the identification of the animal forward and inverse reasoning.

C＋＋编写的机器学习算法 Lemga is a C++ package which consists of classes for several learning models and generic algorithms for optimizing (training) the models-prepared by the machine learning algorithm Lemga C is a package which con sists of classes for several learning models an d generic algorithms for optimizing (training ) the models

命题逻辑中的推理规则可以用来证明一个已经表示成命题公式的定理，但它还不便于机械化实施。因为其中的各条规则都未指明在推导的什麽步骤上应该引入什麽前提或中间结论，这些还有赖于人的经验技巧和才能。1960年王浩提出的算法，可以完全脱离人的经验和技巧，机械地构造每一步推导，证明一个命题逻辑定理的成立。 -Propositional logic in the inference rule can be used to prove that a propositional formula has been expressed as the theorem, but it is not easy to implement mechanization. Because the rules did not specify what steps in the derivation of what should be the introduction of the premise or intermediate conclusions, which also depends on the person s experience of the skills and talent. Wang Hao in 1960 proposed algorithm can be completely divorced from the person s experience and skills, a mechanical structure is derived for each step to prove that a propositional logic theorem establishment.