NEURAL NETWORK-ASSISTED COMPUTER NETWORK MANAGEMENT

摘要

Sequences of computer network log entries indicative of a cause of an event described in a first type of entry are identified by training a long short-term memory (LSTM) neural network to detect computer network log entries of a first type. The network is characterized by a plurality of ordered cells F_i=(x_i, c_i-1, h_i-1) and a final sigmoid layer characterized by a weight vector w^T. A sequence of log entries x_i is received. An h_i for each entry is determined using the trained F_i. A value of gating function G_i(h_i, h_i-1)=II (w^T(h_i−h_i-1)+b) is determined for each entry. II is an indicator function, b is a bias parameter. A sub-sequence of x_i corresponding to G_i(h_i, h_i-1)=1 is output as a sequence of entries indicative of a cause of an event described in a log entry of the first type.