Professional Documents
Culture Documents
Lecture - Naive Bayesian
Lecture - Naive Bayesian
Lecture - Naive Bayesian
m
P (a j | Ci ) P (Ci ) i 1, 2,..., n
j 1
p( yi 1 | xi , ) j xij
By definition p( y i ) xi
1 | xi , . We want to transform the
{0,1}the range restrictions,
probability to remove j as xiθ can take any
real value.
Odds
p : probability of an event
occurring
1 – p : probability of the event not
occurring The odds forp ievent i are then
odd s i
defined as 1 pi
Taking the log of the odds removes the range restrictions.
This way we map the probabilities from the [0; 1] range to the
entire number line (real value).
Odds
p : probability of an event
occurring
1 – p : probability of the event not
occurring The odds forp ievent i are then
odd s i
defined as 1 pi
Taking the log of the odds removes the range restrictions.
This way we map the probabilities from the [0; 1] range to the
entire number line (real value).
pi
log xi
1 p i
pi
xi
1 pi e
e xi 1
pi xi
xi
1 e 1
e Standard logistic sigmoid function
g( )
1
p i g ( t
x) t
1 e
x