While the Thousand Brains Theory is our core model-based, sensorimotor framework for intelligence, HTM is an algorithmic implementation of the Thousand Brains Theory. Based on a wealth of neuroscience evidence, HTM is not just biologically inspired, it is biologically constrained. As we continue to gain a deeper understanding of the brain, both the framework and our terminology have evolved. Notably, HTM Theory has changed to The Thousand Brains Theory of Intelligence.

Learn more about HTM with the resources below:

We make our technology widely accessible in an open-source project. You’ll find our algorithms, source code, and our latest work on applying HTM to today’s machine learning platforms there.

If you’re interested in discussing our work, or developing and implementing our technology, join our open source discussion forum.

This YouTube series is designed to educate the general public about HTM algorithms. Each 10-15 minute episode dives into a particular topic and discusses a component of the Thousand Brains Theory.

  • A Machine Learning Guide to HTM • A guide to resources for anyone with a machine learning background to understand HTM better.
  • HTM Community Github Organization • Our community has created an assortment of HTM implementations, experiments, and integrations available for study and use.
  • HTM Implementations • We have HTM implementations in languages like Python, C++, Java, Clojure, Go, and JavaScript.
  • Translations • We welcome members of the HTM community who want to translate our documentation into languages other than English.

HTM for Anomaly Detection & Prediction

Because of the evolving nature of our theory, our HTM algorithms have also evolved. Our older implementations focused on anomaly detection and prediction, and have been tested and implemented in software. We still think there is value in that work, and have made it available in our open source repositories, but in maintenance mode. You can find more resources below:

Numenta | HTM Applications

Early example applications of HTM technology focused on anomaly detection for streaming data. In order to demonstrate these capabilities, we created example applications.

HTM Studio is a free, desktop tool that lets you find real-time anomalies in your streaming data without having to program, code or set parameters. 

Numenta | Try NAB for Yourself

We created NAB in order to be able to measure and compare results from algorithms designed to find anomalies in streaming data.