Clone this wiki locally
The NuPIC source code is used by Numenta as a part of a commercial product development. Because of this, it is no longer a “pure” implementation of the HTM algorithms. We have made optimizations, added tweaks, and taken some short cuts to improve performance. For those interested in studying and characterizing a purer form of the HTM, please be aware of these changes. If you are interested in using NuPIC in a product, the code may be suitable as-is, or you may wish to make additional changes.
It is useful for understanding and debugging to visualize the state of the CLA at any point during a model's lifetime. There are a few tools for this:
- Cerebro (no longer maintained)
- Cerebro2 (see this video introduction from the 2014 Spring Hackathon)
- NuPIC Studio provides an intuitive HTM construction toolkit and 3D visualizations. Check out the wiki for tutorials.
Numenta engineer Chetan Surpur goes into great detail about the implementations of the spatial and temporal poolers in NuPIC.
Chetan Surpur describes the new Random Distributed Scalar Encoder in NuPIC.
Pages About NuPIC Implementation
- Intro to the Algorithms
- NuPIC Architecture
- Spatial Pooler
- Temporal Pooler
- Online Prediction Framework
- NuPIC API: A Bird's Eye View
- NuPIC Core Network API
- Anomaly Detection
- CLA Classifier
- CLA for Machine Learning / Artificial Intelligence Researchers
- Classifier Algorithms
- Comparing NuPIC to other ML techniques
- Spatial Classification
- Inference Types
|Using NuPIC||Creating Applications|