Learning RMNs
nParameter
estimation is not closed
form
nConvex
problem Þ unique
global maximum
f(Reg1.Grade,Reg2.Grade)
P(Grades,Intelligence|Difficulty)
Difficulty
Difficulty
Intelligence
Intelligence
Intelligence
Grade
Grade
Grade
Grade
low / high
easy / hard
ABC
L = log
Intelligence
Intelligence
Intelligence
Grade
Grade
Grade
Grade
Intelligence
Intelligence
Intelligence
Grade
Grade
Grade
Grade
Maximize