Predict the likelihood that a condition will be satisfied using a recursive neural network

摘要

A method, system, and apparatus comprising a computer program encoded on a computer storage medium that uses a recursive neural network to predict the likelihood that a condition will be satisfied. One of the systems is configured to process a time sequence that includes a respective input at each of a plurality of time steps, one or more recursive neural network layers, and one or more logistic regression nodes Each of the logistic regression nodes corresponds to a respective condition from a predetermined set of conditions, and each of the logistic regression nodes receives the network internal state of the time step for each of a plurality of time steps, and the time One or more logistic regression nodes configured to process the network internal state of the time step according to the current value of the set of parameters of the logistic regression node to generate a future condition score for the corresponding condition of the step Including.