DEVICE FOR ANALYZING TIME SEQUENCE BASED ON RECURRENT NEURAL NETWORK AND ITS METHOD

摘要

PROBLEM TO BE SOLVED: To estimate the probability distribution of time sequence data in a large scale problem at high speed by using the internal state of a neural network. SOLUTION: The realization value of a hidden state vector in a recurrent neural network which expresses a hidden Markovian model is generated as a 'particle' through the use of a Monte Carlo method. At first, (n (j) ) of a time (n) is calculated in terms of recurrent from the forward prediction particle (pn (j) ) of the time (n), the backwards filtering particle (cn+1 (j) ) of the time n+1, observation data xn of the time (n) and the weighting coefficient (n+1 (j) )(S6). Then, the smoothing particle (uu (j) ) of the time (n) is generated by re-extracting the particle from (pn (j) )(S5). Processings S5 and S6 are repeated so as to calculate the aggregation string of the smoothing particles and a probability distribution function is synthesized.