Autonomous Agents Based on Recurrent Neural Networks Applied to Computer Network Management

摘要

With the application of new techniques, such as autonomous agents, artificial neural networks (ANN) and evolutionary computation, new questions arrive and may be, the most important are: " can new problems be solved?" and "with how much effort?" This is particularly important when neural networks are used, since where a new computer paradigm is involved and connectionist computability and complexity theories are missing. To attach this problem we are developing some software autonomous agents based on recurrent neural networks to investigate a form to establish the automation of the computer network management, which is a dynamic process. The first is a simple parity agent that serves as a didactic example. The second is an agent to classify the network events as Critical, Simple or No Failure.