This criterion can be used to train *in classification* a GradientMachine object using the GMTrainer trainer.
This criterion can be used to train *in classification* a GradientMachine object using the GMTrainer trainer. It then maximizes the log likelihood of the data.If we write
for the output
of the GradientMachine, it supposes that
- the outputs
are log-probabilities.
is the probability for the class
![]()
- the predicted class follows a multinomial distribution with parameters
![]()
Alphabetic index HTML hierarchy of classes or Java