A Macrocolumn Architecture Implemented with Spiking Neurons
This work addresses the challenge of building neuromorphic systems for agents to interact with environments, but it appears incremental as it implements an existing state machine model with a specific neuron type.
The paper tackled the problem of implementing a macrocolumn architecture for neuromorphic computing using spiking neurons, and demonstrated its functionality by enabling an agent to learn and navigate 2D environments with pseudo-randomly placed features.
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.