[1week] machine learning overall scenario & end to end code

0. Goal of this lecture

1. Overall scenario of data analysis (ml/dl)

1.1 what is Machine Learning & Deep learning

1.2 kinds of ml

• supervised learning / unsupervised / reinforcement

1.3 problems in ml

(point of Data)

• not enough data
• doesn't have enough Representativeness .
• bad quality data (error ,noisy , outlier)
• not related features (Feature engineering can solve this problem)

(point of Model)

• overfitting
• underfitting

1.4 test& validation