1 Answers
Hierarchical temporal memory is a biologically constrained machine intelligence technology developed by Numenta. Originally described in the 2004 book On Intelligence by Jeff Hawkins with Sandra Blakeslee, HTM is primarily used today for anomaly detection in streaming data. The technology is based on neuroscience and the physiology and interaction of pyramidal neurons in the neocortex of the mammalian brain.
At the core of HTM are learning algorithms that can store, learn, infer, and recall high-order sequences. Unlike most other machine learning methods, HTM constantly learns time-based patterns in unlabeled data. HTM is robust to noise, and has high capacity. When applied to computers, HTM is well suited for prediction, anomaly detection, classification, and ultimately sensorimotor applications.
HTM has been tested and implemented in software through example applications from Numenta and a few commercial applications from Numenta's partners.