NuPIC is an open source general machine intelligence platform, inspired by the human neocortex. In this presentation we’ll walk through what is arguably one of the most intriguing of the many functions that NuPIC’s pattern recognition can serve: location-based anomaly detection.
We’ll review, in a developer-accessible way, the secrets of how NuPIC translates location information (such as GPS data) into the language of the brain and continually learns the patterns, making predictions in real-time.
For a truly immersive demonstration, GPS tracks recorded around the OSCON venue will be encoded and analyzed by NuPIC in real time in front of the audience. These GPS tracks and their resulting anomalies will be displayed on a map while we review them, highlighting interesting points in the data and NuPIC’s analysis.
In another live demo, we’ll fire up a popular video game and export the Cartesian coordinates of the character in the virtual world to NuPIC. Without missing a beat, just as if it were GPS data, we’ll watch NuPIC display its anomaly analysis of the character’s movement in real-time.
As a wrapup, we’ll show several more of the potential ways in which you could use this capability in your own application. We’ll send you on your way with inspiration and excitement by looking at the diverse array of other pattern recognition fields that are already leveraging NuPIC, like modeling energy usage, rogue behavior detection, twitter anomalies, and detecting server anomalies.
Matt Taylor is the open source community flag-bearer for the Numenta Platform for Intelligent Computing. He’s been working with and on open source projects for years, and he spends most of his time managing, encouraging, and interacting with the NuPIC OS community. Originally from a farming community in rural Missouri, Matt has been living in Northern California for over five years, and is finding it hard to leave.
Comments on this page are now closed.
©2015, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org