Lec22.

• 正态分布
• 均匀分布
• 指数分布

Lec23.

**data enhancement:**extrapolate
Texas sharp shooter fallacy(神射手谬误)

股市模拟:

• efficient market hypothesis:有效性市场假说==>随机漫步模型
  • stock & market
  • adjusted for risk
  • distribution
  • multiplicative vs additive
  • memoryless(Poisson):无记忆性

Lec24.

think computationly

computational thinking:

• identify or invent useful abstractions
• formulate solution to a problem as a computational experiment
• design and construct a sufficiently implementation of experiment
• validate experimental setup
• run experment
• evaluate results of experiment
• repeat as needed

Abstraction:

• choosing the right abstractions
• operating in terms of multiple layers of abstractions simultaneously
• defining the relationships the between

Automation:

• think in terms of machineizing our abstractions
• Mechanization is possible

thinking recursively:

• Reformulating a seemingly difficult problem into one which we know how to solve
• Reduction,cmbedding,transformation,simulation

Take it a step at time:

• understand problem
• think about overall structure and algorithm independently of expression in programming language
• break into small parts
• identify useful abstractions
• code and unit test a part at a time
• first functionality, then efficiency
• start with pseudo code

By systematic:

• when debugging, think scientific method
• ask yourself why program did what it did, not why it didn’t do what you wanted it to do.