📗 -> 12/03/24: COURSE QUICK REVIEW


[Lecture Slide Link]

🎤 Vocab

❗ Unit and Larger Context

Small summary

✒️ -> Scratch Notes

Ch.2

Conditional prob, bayes theorem

Bayes Method(ML)

  • P(Class | Feature) = P(Feature|Class)P(Class) / P(Feature)

Ch. 3

E(X) = Long run fraction of outcomes. Mean.

= ith outcome



if independent

Ch. 4

Families of Discrete RVs

  • Uniform
  • Geometric (EX = 1/p)
  • Indicator (EX=p)
  • Binomial
  • Poisson

Ch. 7

Continuous RVs



PDF: . For PDF to exist, must exist and be continuous (differentiable)


Continuous vs Discrete expectation



Families

  • Uniform, Exp., normal

Ch. 11

Normal Dist


CLT

Total of same dist


Z-Transformation


Sample Average





  • is sample variance
  • How does xbar vary?
    • It varies by the var of population over n

Ch. 12-13

Confidence Interval






Hypothesis Testing

Useful when you have a known or asserted statistic

  • IE testing whether smokers and non smokers have the same rate of cancer (diff=0)

Sample stat is telling you different story against sample

Markov Chains

Hot Dogs vs Hambugers

HDHB
HD.8.2
HB.4.6
Property depends on that transitions only dependent on the last state, and not any previous ones (memoryless)

K-Means

Randomly Place Center

  • Calculatate btw each Home and Center A, Center B
  • Place homes in the center they are closer to
  • Replace center and repeat

Linear Regression

Goal is to minimize the error from prediction to actual

y is dependent on x, predict y based on x
(1,2), (2,4), (3,6), y = 0 + 2x

  • Similar to the covariance equation:

Future classes will expand on this to cover new conditions:

  • Prevent over fitting on the input data
  • Use some sort of error function

Resources

  • Put useful links here

Connections