Hierarchical Temporal Memory Theory
Clone this wiki locally
Hierarchical Temporal Memory (HTM)
There are many things humans find easy to do that computers are currently unable to do. Tasks such as visual pattern recognition, understanding spoken language, recognizing and manipulating objects by touch, and navigating in a complex world are easy for humans. Yet despite decades of research, we have few viable algorithms for achieving human-like performance on a computer.
In humans, these capabilities are largely performed by the neocortex. Hierarchal Temporal Memory (HTM) is a technology modeled on how the neocortex performs these functions. It offers the groundwork for building machines that approach or exceed human level performance for many cognitive tasks. HTM is implemented within the NuPIC open source project. NuPIC can run anywhere, including on embedded systems and distributed sensors.
Note: You may notice old references in our documents to the "Cortical Learning Algorithm", or "CLA". These are simply older terms used to describe our Hierarchical Temporal Memory (HTM) technology, which we no longer use.
If you have questions about the theory, or just want to lurk and read others discuss it, you can use the HTM Theory Forum. Jeff Hawkins is a regular user on this forum, so you can ask him questions about his ideas and he might answer as he has the time.
HTM School is an ongoing educational series. See the blog post describing it here. View the first episode here:
Rahul Agarwal, a former-Numenta engineer, gave a great introduction to some of the basics behind the CLA and its implementation within NuPIC. This is a great primer for anyone interested in learning more about how the neocortex works, as well as how it is implemented in NuPIC.
Subutai Ahmad, Numenta VP of Engineering, detailed some aspects of the CLA at our 2013 Fall Hackathon. He discussed an interesting property of SDR's affecting temporal pooling and hierarchies. The interactive session included a lot of Q&A. Slides.
Numenta engineer Chetan Surpur goes into great detail about the implementations of the spatial pooler and temporal memory in NuPIC.
See further discussion on this on our forums: Preliminary details about new theory work on sensory-motor inference
Wiki Pages About Theory
- Reading List
- Cortical Learning Algorithm
- Sparse Distributed Representations
- Hierarchical Temporal Memory
- Jeff's New Ideas About Temporal Pooling
- Sensorimotor Integration
- CLA for ML and AI Researchers
- Community-Provided Content about CLA/HTM
|Installing and Building NuPIC|