Community Created Content

NuPIC Community Content

The following resources have been provided by community members of the NuPIC
open source project and others interested in HTM theory.

Sparse Distributed Representations and Witness Complexes

The goal of this post is (a) to briefly recall what sparse representations are, and (b) how to encode real-world data as sparse representations. We roughly follow Numenta’s approach and connect it to a construction well-known in computational topology called witness complex — a simplicial complex that can be understood as a simplicial approximation of the inputs space.

Mirko Klukas

A Mathematical Formalization of Hierarchical Temporal Memory Cortical Learning Algorithm’s Spatial Pooler

Hierarchical temporal memory (HTM) is an emerging machine learning algorithm, with the potential to provide a means to perform predictions on spatiotemporal data. The algorithm, inspired by the neocortex, currently does not have a comprehensive mathematical framework. This work brings together all aspects of the spatial pooler (SP), a critical learning component in HTM, under a single unifying framework. The primary learning mechanism is explored, where a maximum likelihood estimator for determining the degree of permanence update is proposed. The boosting mechanisms are studied and found to be only relevant during the initial few iterations of the network. Observations are made relating HTM to well known algorithms such as competitive learning and attribute bagging. Methods are provided for using the SP for classification as well as dimensionality reduction. Empirical evidence verifies that given the proper parameterizations, the SP may be used for feature learning.

James Mnatzaganian
Ernest Fokoué
Dhireesha Kudithipudi

NuPIC Studio

NuPIC Studio is an all­-in-­one tool that allows users create a HTM neural network from scratch, train it, collect statistics, and share it among the members of the community.

David Ragazzi and Team

Hierarchal Temporal Memory - Persian

From a student in Artificial Intelligence with a Neural Network course in fall
semester of 2014.

Masoud Abasian

MSc student in Artificial Intelligence

Computer Eng. & Information Tech. Department

Amirkabir University of Technology

Tehran Polytechnic

Toward a Universal Cortical Algorithm

Toward a Universal Cortical Algorithm: Examining Hierarchical Temporal Memory in Light of Frontal Cortical Function

Michael R. Ferrier

Department of Cognitive Linguistic and Psychological Sciences

Brown University

Intelligent Predictions: an empirical study of the Cortical Learning Algorithm (PDF)

Michael Galetzka

Master Thesis for the acquisition of the academic degree Master of Science (M.Sc.)

Blog Posts by Felix Andrews on his HTM Implementation in Clojure

<img src=’//’ alt=‘Example graphic from Felix’s blogs’>

Felix has a series of blog posts about his HTM implementation, comportex, which you can read at

Fergal Byrne on HTM and NuPIC

Papers on HTM by Associate Professor John Thornton (Griffith University)

A look at NuPIC - A self-learning AI engine

This talk discusses Tim McNamara’s experience with NuPIC for building useful artificial intelligence applications. Presented at the Kiwi Pycon in New Zealand.

Understanding the Brain and Building Truly Intelligent Machines

A guest talk by Chetan Surpur for MV Neurosciences.

Nupic on Windows

Installing Nupic on Windows, from Aseem Hegshetye.

Introduction to the CLA Algorithm (PDF)

Detailed document from Christian Cleber Masdeval Braz with wonderful graphics describing the CLA.

Hierarchical Temporal Memory Cortical Learning Algorithm for Pattern Recognition on Multi-core Architectures

By Ryan William Price, Portland State University.