Dimension Reduction and Topic Model
2020-03-01 137浏览
- 1.降维和主题模型 • 小组成员 • 学号： 51174500115 • 学号：51174500003 • 学号： 51174500032 • 学号： 51174500112 • 学号： 52164500021 • 学号： 51174500062 姓名：麻贵龙 姓名：曹阳阳 姓名：李 岩 姓名：刘新韬 姓名：苟长江 姓名：赵 耀
- 2.Principle Component Analysis 麻贵龙
- 3.Outline Principle Component Analysis (PCA) Singular Value Decomposition (SVD) Applications of PCA
- 4.Motion planning • But your planner is only as good as your perception • Perception requires processing sensor data; i.e. finding structure in the data • Some of the most basic processing you can dois:De-noising Dimensionality reduction
- 5.The main idea of PCA • TheGoal:computes the most meaningful basis to re-express a noisy, garbled data set. • High-variance implies high importance Data does not vary much in this direction But how do we compute the high-variance directions? Data varies a lot in this direction
- 6.Maximizing the variance of the projections pre-process thedata:'>data:
