1. Classification
   1. SVM
   2. 二元多類分類器
      1. one-against-one(OAO)
      2. one-against-all(OAA)
   3. Linear discriminant analysis
   4. 決策樹
      1. 類型
         1. 裝袋算法
         2. 回歸樹
         3. 隨機森林
         4. 旋轉森林
         5. 分類樹
   5. 高斯分類器
   6. 羅吉斯回歸(Logistic regression)
   7. KNN
2. Rule-Based
   1. Expert System
3. Backgrond
   1. Feature
      1. SIFT
      2. HOG
   2. Math
      1. 機率密度值
         1. p
         2. ｔ
      2. 母體樣本及抽樣
         1. 信賴區間(Confidence interval)
      3. 變異量
      4. 機率
         1. 貝氏決策法則(Bayesian decision rule)
            1. 事前機率(priori probability)
            2. 概似函數 (likelihood function)
         2. 最大期望演算法（Expectation-maximization algorithm
         3. Gaussian Mixed Model
         4. 機率密度函數
         5. 累積貢獻比率 (Cumulative Proportion)
      5. Euclidean distance
      6. Lagrange
      7. partial differential equation
   3. 相關係數
      1. 皮爾森相關係數(Pearson’s correlation coefficient)
   4. 共變異數(Correlation Coefficient and Covariance)
4. Regression
   1. 線性回歸
   2. 羅吉斯回歸(Logistic regression)
   3. 多元回歸(multiple regression)
5. Clustering
   1. k-means
   2. fuzzy c-means
   3. 高斯混和模型(Gaussian Mixture Model)
   4. EM 演算法(Expectation-Maximization Algorithm, EM)
   5. GMM-EM
6. 模型選擇或評估(Model selection/evaluation)
   1. 交叉驗證(Cross-validation, CV)
      1. Resubstitution
      2. Holdout CV
      3. Leave-one-out CV
      4. K-fold CV
   2. 驗證指標(validation index)
      1. 分類指標
         1. 二元混淆矩陣和相對應驗證指標
         2. ROC曲線
         3. AUC
         4. 多元相關(多元混淆矩陣和相對應驗證指標)
      2. 回歸指標
         1. 平均均方誤差(Mean Squared Error, MSE)
         2. 平均絕對誤差(Mean Absolute Error, MAE)
         3. 平均均方對數誤差(Mean Squared Logarithmic Error, MSLE)
   3. AP/mAP
7. 遷移學習，transfer learning
   1. instance-based transfer learning
   2. feature-representation transfer learning
   3. parameter-transfer learning
   4. relational-knowledge transfer learning
8. Ensemble learning
   1. Bagging
      1. Random Forest
   2. Boosting
   3. Stacking
   4. AdaBoost
9. NN
   1. Perception
   2. 多層感知機(Multilayer perceptron, MLP)
   3. DL
      1. Restricted Boltzmann Machine(RBN)
      2. Deep Belief Networks（DBN）
      3. Generative Adversarial Networks
      4. Deep Neural Network (DNN)
      5. Recurrent Neural Network(RNN)
      6. Convolutional Neural Network(CNN)
         1. Layer
            1. Convolution
            2. pad
            3. kernel_size
            4. num_output
            5. stride
            6. Maxpooling
            7. Flatten
            8. Fully connection
         2. Forwading
            1. Math: Differential
         3. Training
            1. Learning Rate
            2. Stochastic Gradient Descent，SGD
            3. Momentum
            4. Adam
            5. RMSProp
            6. AdaGrad
            7. batch gradient descent
            8. Cost Function
            9. +Normalization
            10. L0
            11. L1
            12. L2
            13. Optimization
            14. Dropout
         4. 交叉驗證(Cross-validation, CV)
            1. Resubstitution
            2. Holdout CV
            3. Leave-one-out CV
            4. K-fold CV
         5. Design
            1. 1×1捲積
      7. Autoencoder
10. Dimension Reduction
    1. 主成分分析(Principle Component Analysis, PCA)
    2. (Linear discriminant analysis Feature Extraction, DAFE)
    3. 矩陣分解(Matrix Factorization)
       1. 交替最小平方法(Alternating least squares, ALS)
       2. 加權交替最小平方法(Alternating-least-squares with weighted-λ -regularization, ALS-WR)
    4. 分散量
       1. 組內分散量(within-class scatter)
       2. 組間分散量(between-class scatter)
11. Reinforcement learning (RL)
    1. Q-learning