machine learning
Three parts of machine learning: programming ability + mathematical statistics knowledge + business knowledge
machine learning classification
1 Supervised learning: e.g. classification, house price prediction
2 Unsupervised learning: e.g. clustering
3 Reinforcement learning: e.g. dynamic systems, robotic control systems
Machine Learning Algorithms
| Is it continuous | unsupervised | supervised |
|---|---|---|
| continuous | Clustering && Dimensionality Reduction | return |
| PCA | Linear Regression/Polynomial Regression | |
| SVD | decision tree | |
| K-means | random forest | |
| Discontinuous | Hidden Markov | Classification |
| Correlation analysis | KNN/Trees | |
| FP-Growth/Apriori | Logistic Regression/Naive Bayes/SVM |
Machine Learning General Ideas
Analyze and obtain multiple features: tall, rich, handsome, potential, etc.;
observe multiple data to obtain each feature value of each data;
design a score function;
design a loss function;
minimize the loss function and obtain the feature weight;
according to the score function , predicting new data.