Assignment 4, Exercise 4.2.2

Master / Vertiefung Künstliche Intelligenz II
1

Disclaimer: Dieser Thread wurde aus dem alten Forum importiert. Daher werden eventuell nicht alle Formatierungen richtig angezeigt. Der ursprüngliche Thread beginnt im zweiten Post dieses Threads.

2

Assignment 4, Exercise 4.2.2
Dear all,

we were wondering about the starting point on exercise 4.2.2. We explored following two paths:

  • Like in the task description: P(Mal, \neg{Men} |F), then normalisation via algorithm in slides
  • Apply Bayes rule first, pack \frac{P(Mal, \neg{Men}}{P(F)} into a variable \alpha and normalize P(F|Mal,\neg{Men}) via algorithm in slides.

The first case looks weird to me, the second case is not suited for a computer algorithm and both yield different results.

So we are a bit clueless and would like to know your opinion :slight_smile:

Thank you and kind regards,
Matthias

3

you’re not supposed to implement it… but:

…how so?

4

This would require that four cases need to be solved for the normalization. Which sounds most reasonable, now that I slept over it :slight_smile:

1 „Gefällt mir“