1.machine learning start (supervised and unsupervised)

1.1 supervised learning（have right answer）

Definition:predicting the unknown based on the known.

Type:

Predict	regression
Classification	multiple inputs ➡ fixed outputs

training set == right answer

1.2 unsupervised learning(have no right answer)

Definition:finding order in disorder.

Type:

Clustering	group similar data points together （e.g.related arcticle recommendation）
Anomoaly detection	find unusual data points
Dimensionality reduction	compress data using fewer numbers