Basis(基礎(chǔ))：

• SSE(Sum of Squared Error, 平方誤差和)
• SAE(Sum of Absolute Error, 絕對(duì)誤差和)
• SRE(Sum of Relative Error, 相對(duì)誤差和)
• MSE(Mean Squared Error, 均方誤差)
• RMSE(Root Mean Squared Error, 均方根誤差)
• RRSE(Root Relative Squared Error, 相對(duì)平方根誤差)
• MAE(Mean Absolute Error, 平均絕對(duì)誤差)
• RAE(Root Absolute Error, 平均絕對(duì)誤差平方根)
• MRSE(Mean Relative Square Error, 相對(duì)平均誤差)
• RRSE(Root Relative Squared Error, 相對(duì)平方根誤差)
• Expectation(期望)&Variance(方差)
• Standard Deviation(標(biāo)準(zhǔn)差，也稱Root Mean Squared Error, 均方根誤差)
• CP(Conditional Probability, 條件概率)
• JP(Joint Probability, 聯(lián)合概率)
• MP(Marginal Probability, 邊緣概率)
• Bayesian Formula(貝葉斯公式)
• CC(Correlation Coefficient, 相關(guān)系數(shù))
• Quantile (分位數(shù))
• Covariance(協(xié)方差矩陣)
• GD(Gradient Descent, 梯度下降)
• SGD(Stochastic Gradient Descent, 隨機(jī)梯度下降)
• LMS(Least Mean Squared, 最小均方)
• LSM(Least Square Methods, 最小二乘法)
• NE(Normal Equation, 正規(guī)方程)
• MLE(Maximum Likelihood Estimation, 極大似然估計(jì))
• QP(Quadratic Programming, 二次規(guī)劃)
• L1 /L2 Regularization(L1/L2正則, 以及更多的, 現(xiàn)在比較火的L2.5正則等)
• Eigenvalue(特征值)
• Eigenvector(特征向量)

Common Distribution(常見分布)：

Discrete Distribution(離散型分布)：

• Bernoulli Distribution/Binomial Distribution(貝努利分布/二項(xiàng)分布)
• Negative Binomial Distribution(負(fù)二項(xiàng)分布)
• Multinomial Distribution(多項(xiàng)分布)
• Geometric Distribution(幾何分布)
• Hypergeometric Distribution(超幾何分布)
• Poisson Distribution (泊松分布)

Continuous Distribution (連續(xù)型分布)：

• Uniform Distribution(均勻分布)
• Normal Distribution/Gaussian Distribution(正態(tài)分布/高斯分布)
• Exponential Distribution(指數(shù)分布)
• Lognormal Distribution(對(duì)數(shù)正態(tài)分布)
• Gamma Distribution(Gamma分布)
• Beta Distribution(Beta分布)
• Dirichlet Distribution(狄利克雷分布)
• Rayleigh Distribution(瑞利分布)
• Cauchy Distribution(柯西分布)
• Weibull Distribution (韋伯分布)

Three Sampling Distribution(三大抽樣分布)：

• Chi-square Distribution(卡方分布)
• t-distribution(t-分布)
• F-distribution(F-分布)

Data Pre-processing(數(shù)據(jù)預(yù)處理)：

• Missing Value Imputation(缺失值填充)
• Discretization(離散化)
• Mapping(映射)
• Normalization(歸一化/標(biāo)準(zhǔn)化)

Sampling(采樣)：

• Simple Random Sampling(簡單隨機(jī)采樣)
• Offline Sampling(離線等可能K采樣)
• Online Sampling(在線等可能K采樣)
• Ratio-based Sampling(等比例隨機(jī)采樣)
• Acceptance-rejection Sampling(接受-拒絕采樣)
• Importance Sampling(重要性采樣)
• MCMC(Markov Chain MonteCarlo 馬爾科夫蒙特卡羅采樣算法：Metropolis-Hasting& Gibbs)

Clustering(聚類)：

• K-MeansK-Mediods
• 二分K-Means
• FK-Means
• Canopy
• Spectral-KMeans(譜聚類)
• GMM-EM(混合高斯模型-期望最大化算法解決)
• K-Pototypes
• CLARANS(基于劃分)
• BIRCH(基于層次)
• CURE(基于層次)
• STING(基于網(wǎng)格)
• CLIQUE(基于密度和基于網(wǎng)格)
• 2014年Science上的密度聚類算法等

Clustering Effectiveness Evaluation(聚類效果評(píng)估)：

• Purity(純度)
• RI(Rand Index, 芮氏指標(biāo))
• ARI(Adjusted Rand Index, 調(diào)整的芮氏指標(biāo))
• NMI(Normalized Mutual Information, 規(guī)范化互信息)
• F-meaure(F測量)

Classification&Regression(分類&回歸)：

• LR(Linear Regression, 線性回歸)
• LR(Logistic Regression, 邏輯回歸)
• SR(Softmax Regression, 多分類邏輯回歸)
• GLM(Generalized Linear Model, 廣義線性模型)
• RR(Ridge Regression, 嶺回歸/L2正則最小二乘回歸)，LASSO(Least Absolute Shrinkage and Selectionator Operator , L1正則最小二乘回歸)
• DT(Decision Tree決策樹)
• RF(Random Forest, 隨機(jī)森林)
• GBDT(Gradient Boosting Decision Tree, 梯度下降決策樹)
• CART(Classification And Regression Tree 分類回歸樹)
• KNN(K-Nearest Neighbor, K近鄰)
• SVM(Support Vector Machine, 支持向量機(jī), 包括SVC(分類)&SVR(回歸))
• CBA(Classification based on Association Rule, 基于關(guān)聯(lián)規(guī)則的分類)
• KF(Kernel Function, 核函數(shù))?
  
  
  • Polynomial Kernel Function(多項(xiàng)式核函數(shù))
  • Guassian Kernel Function(高斯核函數(shù))
  • Radial Basis Function(RBF徑向基函數(shù))
  • String Kernel Function 字符串核函數(shù)
• NB(Naive Bayesian,樸素貝葉斯)
• BN(Bayesian Network/Bayesian Belief Network/Belief Network 貝葉斯網(wǎng)絡(luò)/貝葉斯信度網(wǎng)絡(luò)/信念網(wǎng)絡(luò))
• LDA(Linear Discriminant Analysis/Fisher Linear Discriminant 線性判別分析/Fisher線性判別)
• EL(Ensemble Learning, 集成學(xué)習(xí))?
  
  
  • Boosting
  • Bagging
  • Stacking
  • AdaBoost(Adaptive Boosting 自適應(yīng)增強(qiáng))
• MEM(Maximum Entropy Model, 最大熵模型)

Classification EffectivenessEvaluation(分類效果評(píng)估)：

• Confusion Matrix(混淆矩陣)
• Precision(精確度)
• Recall(召回率)
• Accuracy(準(zhǔn)確率)
• F-score(F得分)
• ROC Curve(ROC曲線)
• AUC(AUC面積)
• Lift Curve(Lift曲線)
• KS Curve(KS曲線)

PGM(Probabilistic Graphical Models, 概率圖模型)：

• BN(BayesianNetwork/Bayesian Belief Network/ Belief Network , 貝葉斯網(wǎng)絡(luò)/貝葉斯信度網(wǎng)絡(luò)/信念網(wǎng)絡(luò))
• MC(Markov Chain, 馬爾科夫鏈)
• MEM(Maximum Entropy Model, 最大熵模型)
• HMM(Hidden Markov Model, 馬爾科夫模型)
• MEMM(Maximum Entropy Markov Model, 最大熵馬爾科夫模型)
• CRF(Conditional Random Field,條件隨機(jī)場)
• MRF(Markov Random Field, 馬爾科夫隨機(jī)場)
• Viterbi(維特比算法)

NN(Neural Network, 神經(jīng)網(wǎng)絡(luò))

• ANN(Artificial Neural Network, 人工神經(jīng)網(wǎng)絡(luò))
• SNN(Static Neural Network, 靜態(tài)神經(jīng)網(wǎng)絡(luò))
• BP(Error Back Propagation, 誤差反向傳播)
• HN(Hopfield Network)
• DNN(Dynamic Neural Network, 動(dòng)態(tài)神經(jīng)網(wǎng)絡(luò))
• RNN(Recurrent Neural Network, 循環(huán)神經(jīng)網(wǎng)絡(luò))
• SRN(Simple Recurrent Network, 簡單的循環(huán)神經(jīng)網(wǎng)絡(luò))
• ESN(Echo State Network, 回聲狀態(tài)網(wǎng)絡(luò))
• LSTM(Long Short Term Memory, 長短記憶神經(jīng)網(wǎng)絡(luò))
• CW-RNN(Clockwork-Recurrent Neural Network, 時(shí)鐘驅(qū)動(dòng)循環(huán)神經(jīng)網(wǎng)絡(luò), 2014ICML）等.

Deep Learning(深度學(xué)習(xí))：

• Auto-encoder(自動(dòng)編碼器)
• SAE(Stacked Auto-encoders堆疊自動(dòng)編碼器)?
  
  
  • Sparse Auto-encoders(稀疏自動(dòng)編碼器)
  • Denoising Auto-encoders(去噪自動(dòng)編碼器)
  • Contractive Auto-encoders(收縮自動(dòng)編碼器)
• RBM(Restricted Boltzmann Machine, 受限玻爾茲曼機(jī))
• DBN(Deep Belief Network, 深度信念網(wǎng)絡(luò))
• CNN(Convolutional Neural Network, 卷積神經(jīng)網(wǎng)絡(luò))
• Word2Vec(詞向量學(xué)習(xí)模型)

Dimensionality Reduction(降維)：

• LDA(Linear Discriminant Analysis/Fisher Linear Discriminant, 線性判別分析/Fish線性判別)
• PCA(Principal Component Analysis, 主成分分析)
• ICA(Independent Component Analysis, 獨(dú)立成分分析)
• SVD(Singular Value Decomposition 奇異值分解)
• FA(Factor Analysis 因子分析法)

Text Mining(文本挖掘)：

• VSM(Vector Space Model, 向量空間模型)
• Word2Vec(詞向量學(xué)習(xí)模型)
• TF(Term Frequency, 詞頻)
• TF-IDF(TermFrequency-Inverse Document Frequency, 詞頻-逆向文檔頻率)
• MI(Mutual Information, 互信息)
• ECE(Expected Cross Entropy, 期望交叉熵)
• QEMI(二次信息熵)
• IG(Information Gain, 信息增益)
• IGR(Information Gain Ratio, 信息增益率)
• Gini(基尼系數(shù))
• x2 Statistic(x2統(tǒng)計(jì)量)
• TEW(Text Evidence Weight, 文本證據(jù)權(quán))
• OR(Odds Ratio, 優(yōu)勢率)
• N-Gram Model
• LSA(Latent Semantic Analysis, 潛在語義分析)
• PLSA(Probabilistic Latent Semantic Analysis, 基于概率的潛在語義分析)
• LDA(Latent Dirichlet Allocation, 潛在狄利克雷模型)
• SLM(Statistical Language Model, 統(tǒng)計(jì)語言模型)
• NPLM(Neural Probabilistic Language Model, 神經(jīng)概率語言模型)
• CBOW(Continuous Bag of Words Model, 連續(xù)詞袋模型)
• Skip-gram(Skip-gram Model)

Association Mining(關(guān)聯(lián)挖掘)：

• Apriori算法
• FP-growth(Frequency Pattern Tree Growth, 頻繁模式樹生長算法)
• MSApriori(Multi Support-based Apriori, 基于多支持度的Apriori算法)
• GSpan(Graph-based Substructure Pattern Mining, 頻繁子圖挖掘)

Sequential Patterns Analysis(序列模式分析)

• AprioriAll
• Spade
• GSP(Generalized Sequential Patterns, 廣義序列模式)
• PrefixSpan

Forecast(預(yù)測)

• LR(Linear Regression, 線性回歸)
• SVR(Support Vector Regression, 支持向量機(jī)回歸)
• ARIMA(Autoregressive Integrated Moving Average Model, 自回歸積分滑動(dòng)平均模型)
• GM(Gray Model, 灰色模型)
• BPNN(BP Neural Network, 反向傳播神經(jīng)網(wǎng)絡(luò))
• SRN(Simple Recurrent Network, 簡單循環(huán)神經(jīng)網(wǎng)絡(luò))
• LSTM(Long Short Term Memory, 長短記憶神經(jīng)網(wǎng)絡(luò))
• CW-RNN(Clockwork Recurrent Neural Network, 時(shí)鐘驅(qū)動(dòng)循環(huán)神經(jīng)網(wǎng)絡(luò))
• ……

Linked Analysis(鏈接分析)

• HITS(Hyperlink-Induced Topic Search, 基于超鏈接的主題檢索算法)
• PageRank(網(wǎng)頁排名)

Recommendation Engine(推薦引擎)：

• SVD
• Slope One
• DBR(Demographic-based Recommendation, 基于人口統(tǒng)計(jì)學(xué)的推薦)
• CBR(Context-based Recommendation, 基于內(nèi)容的推薦)
• CF(Collaborative Filtering, 協(xié)同過濾)
• UCF(User-based Collaborative Filtering Recommendation, 基于用戶的協(xié)同過濾推薦)
• ICF(Item-based Collaborative Filtering Recommendation, 基于項(xiàng)目的協(xié)同過濾推薦)

Similarity Measure&Distance Measure(相似性與距離度量)：

• EuclideanDistance(歐式距離)
• Chebyshev Distance(切比雪夫距離)
• Minkowski Distance(閔可夫斯基距離)
• Standardized EuclideanDistance(標(biāo)準(zhǔn)化歐氏距離)
• Mahalanobis Distance(馬氏距離)
• Cos(Cosine, 余弦)
• Hamming Distance/Edit Distance(漢明距離/編輯距離)
• Jaccard Distance(杰卡德距離)
• Correlation Coefficient Distance(相關(guān)系數(shù)距離)
• Information Entropy(信息熵)
• KL(Kullback-Leibler Divergence, KL散度/Relative Entropy, 相對(duì)熵)

Optimization(最優(yōu)化)：

Non-constrained Optimization(無約束優(yōu)化)：

• Cyclic Variable Methods(變量輪換法)
• Variable Simplex Methods(可變單純形法)
• Newton Methods(牛頓法)
• Quasi-Newton Methods(擬牛頓法)
• Conjugate Gradient Methods(共軛梯度法)。

Constrained Optimization(有約束優(yōu)化)：

• Approximation Programming Methods(近似規(guī)劃法)
• Penalty Function Methods(罰函數(shù)法)
• Multiplier Methods(乘子法)。
• Heuristic Algorithm(啟發(fā)式算法)
• SA(Simulated Annealing, 模擬退火算法)
• GA(Genetic Algorithm, 遺傳算法)
• ACO(Ant Colony Optimization, 蟻群算法)

Feature Selection(特征選擇)：

• Mutual Information(互信息)
• Document Frequence(文檔頻率)
• Information Gain(信息增益)
• Chi-squared Test(卡方檢驗(yàn))
• Gini(基尼系數(shù))

Outlier Detection(異常點(diǎn)檢測)：

• Statistic-based(基于統(tǒng)計(jì))
• Density-based(基于密度)
• Clustering-based(基于聚類)。

Learning to Rank(基于學(xué)習(xí)的排序)：

• Pointwise?
  
  
  • McRank
• Pairwise?
  
  
  • RankingSVM
  • RankNet
  • Frank
  • RankBoost；
• Listwise?
  
  
  • AdaRank
  • SoftRank
  • LamdaMART

Tool(工具)：

• • MPI
  • Hadoop生態(tài)圈
  • Spark
  • IGraph
  • BSP
  • Weka
  • Mahout
  • Scikit-learn
  • PyBrain
  • Theano?
    
    

轉(zhuǎn)載于:https://www.cnblogs.com/baiboy/p/dm1.html

總結(jié)

以上是生活随笔為你收集整理的NLP数据挖掘基础知识的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。