Royal Bank of Canada
SYSTEM AND METHOD FOR MACHINE LEARNING ARCHITECTURE WITH VARIATIONAL AUTOENCODER POOLING

Abstract:

A computer implemented method is described for conducting text sequence machine learning, the method comprising: receiving an input sequence x=[x.sub.1, x.sub.2, . . . , x.sub.n], to produce a feature vector for a series of hidden states h.sub.x=[h.sub.1, h.sub.2, . . . , h.sub.n], wherein the feature vector for the series of hidden states h.sub.x is generated by performing pooling over a temporal dimension of all hidden states output by the encoder machine learning data architecture; and extracting from the series of hidden states h.sub.x, a mean and a variance parameter, and to encapsulate the mean and the variance parameter as an approximate posterior data structure.