Search - ie - CodeBus

Search - ie - List

[AI-NN-PR] tsp(2) DL : 0: 本程序实现了多城市的tsp问题（即旅行商问题）的遗传算法-the process of multi-city tsp (ie, the traveling salesman problem) Genetic Algorithm
Date : 2026-01-10 Size : 1.12mb User : 叶靥
[AI-NN-PR] c++neuralnetworkdevelopmentpakage DL : 0: annie is an ANN, ie, Artificial Neural Network library developed in C++. It can be used to implement various kinds of neural networks like Multi-Layer Perceptron, Radial basis function networks, Hopfield networks etc.-ANN, ie, Artificial Neural Network library developed i n C. It can be used to implement various kinds of n Eural networks like Multi-Layer 102206. Radial basis function networks, Hopfield networks etc.
Date : 2026-01-10 Size : 481kb User : 陈伟
[AI-NN-PR] marq DL : 0: ％ Train a two layer neural network with the Levenberg-Marquardt ％ method. ％％ If desired, it is possible to use regularization by ％ weight decay. Also pruned (ie. not fully connected) networks can ％ be trained. ％％ Given a set of corresponding input-output pairs and an initial ％ network, ％ [W1,W2,critvec,iteration,lambda]=marq(NetDef,W1,W2,PHI,Y,trparms) ％ trains the network with the Levenberg-Marquardt method. ％％ The activation functions can be either linear or tanh. The ％ network architecture is defined by the matrix NetDef which ％ has two rows. The first row specifies the hidden layer and the ％ second row specifies the output layer.- Train a two layer neural network with the Levenberg-Marquardt method. If desired, it is possible to use regularization by weight decay. Also pruned (ie. not fully connected) networks can be trained. Given a set of corresponding input-output pairs and an initial network, [W1, W2, critvec, iteration, lambda] = marq (NetDef, W1, W2, PHI, Y, trparms) trains the network with the Levenberg-Marquardt method . The activation functions can be either linear or tanh. The network architecture is defined by the matrix NetDef which has two rows. The first row specifies the hidden layer and the second row specifies the output layer.
Date : 2026-01-10 Size : 3kb User : 张镇
[AI-NN-PR] simpelpso DL : 0: written by budi santosa to implement modified PSO on single variable function budi_s@ie.its.ac.id based on Engineering Optimization Theory and Practice book by Singiresu S. Rao- written by budi santosa to implement modified PSO on single variable function budi_s@ie.its.ac.id based on Engineering Optimization Theory and Practice book by Singiresu S. Rao
Date : 2026-01-10 Size : 1kb User : budi santosa
[AI-NN-PR] bpdetail DL : 0: 严格按照BP网络计算公式来设计的一个matlab程序,对BP网络进行了优化设计优化1：设计了yyy，即在o(k)计算公式时，当网络进入平坦区时(<0.0001)学习率加大，出来后学习率又还原优化2：v(i,j)=v(i,j)+deltv(i,j)+a*dv(i,j) -BP network in strict accordance with the formula to design a matlab program, the BP network optimization optimized 1: Design of yyy, ie o (k) formula, when the network into the flat zone ( " 0.0001) learning rate increased, came out again to restore the learning rate optimization of 2: v (i, j) = v (i, j)+ deltv (i, j)+ a* dv (i, j)
Date : 2026-01-10 Size : 2kb User : 沈龙
[AI-NN-PR] apriori DL : 0: Apriori算法【l】：1994年由R．Agrawal等人提出来的Apriori算法是关联规则挖掘的一个经典算法，后来的许多算法都是基于该算法的思想。算法的名称来源于在算法中应用了频繁项集的先验知识，即：一个频繁项集的任一非空子集必定是频繁项集；因此只要某一项集是非频繁的，则其超集就无须再检验。-Apriori algorithm】【l: 1994 by R. Agrawal et al to the Apriori algorithm is a classical association rule mining algorithm, and later many of the algorithms are based on the idea of the algorithm. The name comes from the algorithm applied in the algorithm a priori knowledge of frequent item sets, ie: any of a frequent itemset must be a non-empty subset of frequent item sets so long as a particular set of non-frequent, its superset to no longer need to test.
Date : 2026-01-10 Size : 201kb User : plairstar
[AI-NN-PR] ACA-TSP_source_code DL : 0: 该代码是基于蚁群算法的matlab代码，适用于求解TSP问题（即旅行商问题）-The code is based on ant colony algorithm matlab code for solving the TSP problem (ie TSP)
Date : 2026-01-10 Size : 1kb User : xyh
[AI-NN-PR] A_very_sim977756232002-457852ngfppr2567 DL : 0: A very simple example of Neural Networks using back propagation This program is a simple example of Neural Networks using back propagation. My code has all basic functionalities like learning rate, load net, save net, etc. You can have as many layers as you can. The code here is extensible ie you can use my code in your programs to implement neural networks. Here a sample problem and network is given. Load the network with name "XOR.nn". It solves XOR problem. Please don t forget to give comments, credits and most important your VOTE!. And note if Neural Networks and back propagation is a mystery for you I can write a tutorial on nn and back propagation. Just tell me, if you want it, via feedback. And also, if you create another application using my neural networks please inform me. MadeBy: Paras Chopra CEO, NaramCheez paraschopra@lycos.com - A very simple example of Neural Networks using back propagation This program is a simple example of Neural Networks using back propagation. My code has all basic functionalities like learning rate, load net, save net, etc. You can have as many layers as you can. The code here is extensible ie you can use my code in your programs to implement neural networks. Here a sample problem and network is given. Load the network with name "XOR.nn". It solves XOR problem. Please don t forget to give comments, credits and most important your VOTE!. And note if Neural Networks and back propagation is a mystery for you I can write a tutorial on nn and back propagation. Just tell me, if you want it, via feedback. And also, if you create another application using my neural networks please inform me. MadeBy: Paras Chopra CEO, NaramCheez paraschopra@lycos.com
Date : 2026-01-10 Size : 6kb User : ani
[AI-NN-PR] anfisExample_book- DL : 0: 这个是我看文献做的一个anfis(自适应神经网络模糊推理系统)的一个例子，已经表明注释，很容易上手-This is a code for anfis(Adaptive network-based fuzzy inference system),when you looke ie you can got it!
Date : 2026-01-10 Size : 1.42mb User : 吴遇桑
[AI-NN-PR] dijstra DL : 0: 网络层的状态路由法，即dijkstra算法-State routing method, ie dijkstra algorithm
Date : 2026-01-10 Size : 522kb User : 康健
[AI-NN-PR] Genetic-algorithm-optimization DL : 0: 遗传算法优化B P神经网络的目的是通过遗传算法得到更好的网络初始权值和阈值, 其基本思想就是用个体代表网络的初始权值和阈值、个体值初始化的B P神经网络的预测误差作为该个体的适应度值, 通过选择、交叉、变异操作寻找最优个体, 即最优的B P神经网络初始权值。除了遗传算法之外, 还可以采用粒子群算法、蚁群算法等优化B P神经网络初始权值。-Genetic algorithm to optimize BP neural network is designed by means of genetic algorithms get better network initial weights and thresholds, the basic idea is to use individual represents the network' s initial weights and thresholds, the individual values initialized BP neural network prediction error as the individual' s fitness value, through selection, crossover and mutation to find the optimal individual, ie the optimal BP neural network initial weights. In addition to genetic algorithms, you can also use particle swarm optimization, ant colony algorithm to optimize BP neural network initial weights.
Date : 2026-01-10 Size : 51kb User : 吴江
[AI-NN-PR] Ant_AI DL : 0: “ 人工蚂蚁” 生活在一个二维网格世界中，它能沿已作标记的单元所组成的连续“信息素踪迹”(宽为一个单元)的运动。这个蚂蚁占一个单元，它可以面向东、南、西、北。它能做五个动作：前移一个单元(m)；在同一单元中向左转(l)；在同一单元中向右转(r)；设置状态位元“开”(on)；设置状态位元“关”(off)。蚂蚁感知它的正前方(即其面朝的方向)是否有信息素踪迹且其状态位元是否为“开”，若状态位元为“开”表示该单元已经走过（设状态位元起初为“关”）。-"Artificial ants world live in a two-dimensional grid, it can be marked along the unit has been composed of continuous" pheromone trail "(width of a cell) movement. The ants representing a unit, it can be facing east, south, west and north. It can do five actions: move forward one unit (m) switch (l) to the left in the same unit rpm (r) to the right in the same unit setting status bit to "On" (on) setting status bit "off" (off). Ants perceive it in front (ie, facing the direction of) whether pheromone trail and its status bit is "open", if the status bit is "open" means that the unit has gone through (initially set status bits "Off").
Date : 2026-01-10 Size : 991kb User : 李玫
[AI-NN-PR] CNN DL : 0: 卷积神经网络是一种特殊的深层的神经网络模型，它的特殊性体现在两个方面，一方面它的神经元间的连接是非全连接的，另一方面同一层中某些神经元之间的连接的权重是共享的（即相同的）。它的非全连接和权值共享的网络结构使之更类似于生物神经网络，降低了网络模型的复杂度（对于很难学习的深层结构来说，这是非常重要的），减少了权值的数量。-Convolution neural network is a kind of special deep neural network model, its particularity manifests in two aspects, on one hand its neurons connection is not completely connected, on the other hand the same layer in some neurons The weights of the connections are shared (ie, the same). Its non-fully connected and weight-sharing network structure makes it more similar to the biological neural network, reducing the complexity of the network model (it is very important for the deep structure that is difficult to learn), reducing the weight quantity.
Date : 2026-01-10 Size : 6kb User : 夏雪
[AI-NN-PR] ML-kNN DL : 0: 本程序实现了融合最近邻的ML-KNN算法（即IML-KNN），与KNN进行比较，分类效果更好。-This procedure to achieve the fusion of the nearest neighbor ML-KNN algorithm (ie IML-KNN), compared with KNN, better classification effect.
Date : 2026-01-10 Size : 2.87mb User : 周鑫
[AI-NN-PR] 七段数码管接口 DL : 0: gfnqjgq服务费违反违反违反违反1赴全国副IE七八个覅部分还不放假而不服你和覅?很方便开办(wrgnjwhg hwgfhqgfhqbfkjqhfjqhfjq)
Date : 2026-01-10 Size : 382kb User : fnqefhbqe
[AI-NN-PR] 基于蚁群算法的二维路径规划算法 DL : 0: 而一个种群则由经过基因（gene）编码的一定数目的个体(individual)组成。每个个体实际上是染色体(chromosome)带有特征的实体。染色体作为遗传物质的主要载体，即多个基因的集合，其内部表现（即基因型）是某种基因组合，它决定了个体的形状的外部表现，如黑头发的特征是由染色体中控制这一特征的某种基因组合决定的。(A population consists of a certain number of individuals encoded by a gene. Each individual is actually an entity with a chromosome. Chromosome as a major carrier of genetic material, that is, a collection of multiple genes, the internal performance (ie, genotype) is a combination of certain genes, which determine the external shape of the individual performance, such as the characteristics of black hair is controlled by the chromosome A combination of certain characteristics of a gene.)
Date : 2026-01-10 Size : 3kb User : 鲁小胖1
[AI-NN-PR] BayesKit DL : 0: 贝叶斯网络，又称信念网络(Belief Network, BN), 或有向无环图模型，是由一个有向无环图(DAG,Directed acyclic graphical model)和条件概率分布(即知道P(xi|parent(xi))发生的概率构成，其中parent(xi)为指向xi的直接父节点)。它是一种模拟人类推理过程中因果关系的不确定性处理模型，其网络拓朴结构是一个有向无环图(DAG)。(Bayesian networks, also known as belief networks (Belief Network, BN), or directed acyclic graph models, are composed of a Directed acyclic graphical model (DAG) and a conditional probability distribution (ie know P(xi) |parent(xi)) Probability of occurrence, where parent(xi) is the direct parent to xi. It is an uncertainty processing model that simulates causality in human reasoning. Its network topology is a directed acyclic graph (DAG).)
Date : 2026-01-10 Size : 25kb User : 耿子