About the HTM Theory category


Discussions about HTM theory, not software implementations of the theory.

Posting Guidelines

This is a list for discussing theoretical aspects of HTM theory. It is not a list for general discussions of AI and machine learning. There are other good groups for non-HTM discussions like comp.ai.neural-nets and comp.ai.philosophy.

Here are some examples of appropriate topics and examples of topics that are best discussed elsewhere.


  • Mathematical analysis or empirical results of HTM theory
  • Theoretical extensions of HTM theory
  • Biological findings that relate to HTM theory


  • Proposals for alternate approaches to machine intelligence
  • Extensions to HTMs that are not biologically plausible
  • AI or neural network theories that are not based on SDRs, temporal
    memory, pooling, and hierarchy
  • Detailed questions about NuPIC or other HTM implementation codebases (see the specific categories for NuPIC, HTM.Java, and Comportex for those questions)

For example: a discussion of using SDRs and HTM temporal memory for
natural language processing is an appropriate topic, but a general
discussion of language theory is not.

Another example: a discussion of how to extend HTM to incorporate
goal-oriented behavior is appropriate, but general discussions of
robotics is not.

Historical Content

This forum was migrated from the nupic-theory mailing list. Here is an archive of all conversations from that list: