Diiusion of Credit in Markovian Models

This paper studies the problem of diiusion in Markovian models, such as hidden Markov models (HMMs) and how it makes very diicult the task of learning of long-term dependencies in sequences. Using results from Markov chain theory, we show that the problem of diiusion is reduced if the transition probabilities approach 0 or 1. Under this condition, standard HMMs have very limited modeling capabilities, but input/output HMMs can still perform interesting computations.