Closed Singh-Sonam closed 2 years ago
You probably want to use the formula here https://en.wikipedia.org/wiki/Bayesian_information_criterion. The log of the likelihood can directly come from SHMM.log_likelihood, after you finish training the model. The other parameters you should be able to count yourself.
Thank You. Just wanted to make sure.
Hi could you please let me know how can I get the AIC/BIC for UnSupervisedIOHMM to get the optimal hidden states. Thank you for your help.