I am confused, I thought we were to weight hypotheses by 2^-(kolmogorov(H)) not 2^-length(H). Am I missing something?
Yes, length there is short for “minimum message length” or in other words Kolmogorov complexity.
I am confused, I thought we were to weight hypotheses by 2^-(kolmogorov(H)) not 2^-length(H). Am I missing something?
Yes, length there is short for “minimum message length” or in other words Kolmogorov complexity.