Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

In this paper (Products of Hidden Markov Models, http://www.cs.toronto.edu/~hinton/absps/aistats_2001.pdf), the authors say that:

The hidden state of a single HMM can only convey log K bits of information about the recent history.

K being the number of states. I was trying to understand what they mean and came up with the following: imagine I have 4 states: <0-0>, <0-1>, <1-0>, <1-1>. These 4 states convey log(4)=2 bits of information, A and B, each of which can have values 0 or 1 (e.g. state with A=1 and B=0 is <1-0>).

However, I'm not sure if this is the correct reasoning.

share|improve this question

1 Answer 1

up vote 2 down vote accepted

In $n$ bits you can encode up to $2^n$ states (that's the total amount of information available in $n$ bits).
In reverse, to encode $K$ states you'll need at least $log(K)$ bits.

share|improve this answer

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.