LEARNING DEPENDENCIES OF PERFORMANCE METRICS USING RECURRENT NEURAL NETWORKS

摘要

A processor receives time series data and a function describing a type of dependency that is desired to be determined from the time series data. A probe matrix is determined based upon the function. A weight matrix including a plurality of weights is determined, and a weighted probe matrix is determined based upon the probe matrix and the weighted matrix. The time series data and the weighted probe matrix is input into a neural network, and the neural network is trained using the time series data and the weighted probe matrix to converge the plurality of weights in the weight matrix. The converged weight matrix is extracted from an output of the neural network, and dependencies in the time series data are determined based upon the converged weight matrix.