The mission of this project is to build and support a community interested in machine learning and machine intelligence based on modeling the neocortex and the principles upon which it works.
NuPIC, the Numenta Platform for Intelligent Computing, comprises a set of learning algorithms that were first described in a white paper published by Numenta in 2009. The learning algorithms faithfully capture how layers of neurons in the neocortex learn. The white paper has been translated into seven languages by volunteers and has generated considerable interest among developers and research scientists.
We created the NuPIC open source project because people read the white paper and wanted to work with these algorithms. They asked us to make them available in an open source project. For a detail explanation of our motivations, hopes and fears around this project, see Jeff’s Introduction to NuPIC.
At the heart of NuPIC is Hierarchical Temporal Memory, or HTM. HTM has a deep biological mapping which will be interesting to neuroscientists. From an algorithmic point of view there are three principle properties.
We believe HTM is an essential component of biological intelligence and will likely prove to be a central component of machine intelligence. We anticipate that over time HTM will be embedded in hierarchical systems with distributed sensors, behavior, and attention.
Are you interested in learning more about the brain-inspired Hierarchical Temporal Memory Numenta has developed over the past several years? Or maybe you just want to check out our open source software, NuPIC. You might even want to better understand what Numenta is all about. Are you ready to interact with our community? Then join our mailing list and ask us some questions!