Based on a wealth of neuroscience evidence we have created HTM (Hierarchical Temporal Memory), a theoretical framework for both biological and machine intelligence. When applied to computers, HTM is well suited for prediction, anomaly detection, classification and ultimately sensori-motor applications.
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 learns time-based patterns in unlabeled data on a continuous basis. HTM is robust to noise, and high capacity, meaning that it can learn multiple patterns simultaneously.
HTM works best with data that meets the following characteristics:
- Streaming data rather than batch data files
- Data with time-based patterns
- Many individual data sources where hand crafting separate models is impractical
- Subtle patterns that can’t always be seen by humans
- Data for which simple techniques such as thresholds yield substantial false positives and false negatives
Our technology has been tested and implemented in software, all of which is developed with best practices and suitable for deploying in commercial applications.