# A Macrocolumn Architecture Implemented with Spiking Neurons

arXiv: https://arxiv.org/abs/2207.05081 · HTML: https://mlsanity.com/paper/2207.05081/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 38 references that are in the map.
- First posted on arXiv 11 Jul 2022.

## Builds on (most cited first, 5 of 5)

- [Why Neurons Have Thousands of Synapses, A Theory of Sequence Memory in Neocortex](https://mlsanity.com/paper/1511.00083/) (2015)
- [A Temporal Neural Network Architecture for Online Learning](https://mlsanity.com/paper/2011.13844/) (2020)
- [(Newtonian) Space-Time Algebra](https://mlsanity.com/paper/2001.04242/) (2019)
- [A Neuromorphic Paradigm for Online Unsupervised Clustering](https://mlsanity.com/paper/2005.04170/) (2020)
- [Implementing Online Reinforcement Learning with Temporal Neural Networks](https://mlsanity.com/paper/2204.05437/) (2022)

## Built on by (most cited first, 1 of 1)

- [Neuromorphic Online Clustering and Its Application to Spike Sorting](https://mlsanity.com/paper/2506.12555/) (2025)

## Abstract (arXiv)

The macrocolumn is a key component of a neuromorphic computing system that interacts with an external environment under control of an agent. Environments are learned and stored in the macrocolumn as labeled directed graphs where edges connect features and labels indicate the relative displacements between them. Macrocolumn functionality is first defined with a state machine model. This model is then implemented with a neural network composed of spiking neurons. The neuron model employs active dendrites and mirrors the Hawkins/Numenta neuron model. The architecture is demonstrated with a research benchmark in which an agent employs a macrocolumn to first learn and then navigate 2-d environments containing pseudo-randomly placed features.