Numenta

Numenta, is inspired by machine learning technology and is based on a theory of the neocortex. The technology can be applied to anomaly detection in servers and applications, human behavior, geo-spatial tracking data, and to the predication and classification of natural language. Numenta has created NuPIC (Numenta Platform for Intelligent Computing) as an open source project.

Applications include detects anomalies in publicly traded companies, models stock price, stock volume, and Twitter volume related to top market companies, detects anomalies in servers and applications. Learns continuously, automatically discovers time-based patterns in data, and generalizes from experience.

Early anomaly detection in streaming data is as difficult as it is important. Numenta Anomaly Benchmark (NAB) is an open source framework that anyone can use to test and compare real-time anomaly detection algorithms. It consists of a dataset with 58 real-world, labeled data files and a scoring mechanism that rewards early detection and on-line learning .