搜索资源列表
arrhythmia_paper
- Paper on random forest , ANN , LinearSVM , Logistic regression classifiers
极限学习机
- 极限学习机分类器,训练函数与预测函数,以及数据实例(Extreme Machine Classifiers, Training and Prediction Functions, and Data Instances)
lhisft
- Learning Kernel Classifiers Theory and Algorithms, Introducti()
decaptcha-master
- A CAPTCHA Breaker using k-Nearest Neighbor Classifiers, Support Vector Machines, and Neural Networks.
mytensorflow
- tensorflow学习笔记,其中包含了几总分类器,和tensorflow框架的部分具有代表性的代码(Tensorflow learning notes, which contain several general classifiers, and some representative codes of the tensorflow fr a mework.)
mnist
- 使用了全连接网络,卷积神经网络,循环神经网络分别构建不同的分类器,如何通过模型保存原理进行保存。(Using the fully connected network and convolution neural network, recurrent neural network builds different classifiers respectively, and how to save them through the pres
vote
- 可以集成多个分类器的投票算法,采用python实现(The voting algorithm of multiple classifiers can be integrated and implemented by python.)
balancevote
- 针对不平衡样本的,可以综合多个分类器的投票算法。(For the unbalanced samples, the voting algorithm of multiple classifiers can be synthesized.)
lrrfgbdtxgboost
- 用Xgboost作为集成算法,将LR,RF,GBDT三个分类器的结果综合起来。(Using Xgboost as an ensemble algorithm, we synthesize the results of three classifiers of LR, RF and GBDT.)
classifier
- 一些分类器尝试,包括SVM,KNN,自带树与adaboost或者bagging结合等。(Some classifiers test,such as SVM,KNN,etc, including test data. Only some of the methods are included in the main.m.)
nichingparticle-swarm-optimization
- 粒子群优化算起源于对鸟群、鱼群以及对某些社会行为的模拟,是一种基于群体智能的进化计算技术。而小生境技术则起源于遗传算法,这种方法能使基于群体的随机优化算法形成物种,从而使相应的优化算法具有发现多个最优解的能力。而多分类器集成技术则是通过多个分类器进行某种组合来决定最终的分类,以取得比单个分类器更好的性能。多分类器集成技术要求基元分类器不仅个体性能要好并且其差异度要大,这与小生境技术形成物种的能力具有很多内在的相似性。目前己经有研究者将小
MATLABcode
- 采用bp对男女生样本数据中的身高,体重,喜欢数学,喜欢文学,喜欢运动,设计男女生分类器,并计算模型预测性能(包含SE,SP,ACC和AUC )。(Using bp for height and weight in male and female sample data, like math, like literature, like sports, design boys and girls classifiers, and calc
sklearn-tree-BN-knn
- 分类器的性能比较与调优: 使用scikit-learn 包中的tree,贝叶斯,knn,对数据进行模型训练,尽量了解其原理及运用。 使用不同分析三种分类器在实验中的性能比较,分析它们的特点。 本实验采用的数据集为house与segment。(Performance comparison and optimization of classifiers: We use tree, Bayesian and KNN in scikit