A Macrocolumn Architecture Implemented with Spiking Neurons

TL;DR

This paper presents a macrocolumn architecture using spiking neurons, capable of learning and navigating 2D environments by modeling environment features as labeled graphs, inspired by biological neural structures.

Contribution

It introduces a novel macrocolumn implementation with spiking neurons based on active dendrites, integrating a state machine model for environment learning and navigation.

Findings

Successfully learned and navigated 2D environments

Demonstrated the neural implementation of environment graphs

Showed potential for neuromorphic computing applications

Abstract

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.