On the Learnability of Hidden Markov Models [chapter]

Sebastiaan A. Terwijn
2002 Lecture Notes in Computer Science  
A simple result is presented that links the learning of hidden Markov models to results in complexity theory about nonlearnability of finite automata under certain cryptographic assumptions. Rather than considering all probability distributions, or even just certain specific ones, the learning of a hidden Markov model takes place under a distribution induced by the model itself.
doi:10.1007/3-540-45790-9_21 fatcat:7wt7t4gsczc37dxqchsuk6jtz4