Anomaly Detection with HTM
Kjell Jorgen Hole · 2016
We model information and communications technology (ICT) systems as complex adaptive systems. Since we cannot hope to predict all future incidents in complex systems, real-time monitoring is needed to detect local failures before they propagate into global failures with an intolerable impact. In particular, monitoring is required to determine the consequences of injecting artificial errors into production systems and to learn how to avoid or limit the impact of future incidents. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.