Assembling Modular, Hierarchical Cognitive Map Learners with Hyperdimensional Computing

TL;DR

This paper introduces hyperdimensional computing-based cognitive map learners that can be reused for different tasks like the Tower of Hanoi puzzle without retraining, advancing modular and biologically plausible AI systems.

Contribution

It presents a novel approach to creating modular, hierarchical cognitive map learners using hyperdimensional computing, enabling flexible reuse and abstraction in AI.

Findings

HDC-based CMLs can be repurposed for new tasks without retraining.

CMLs perform near-optimal path planning in abstract graphs.

The approach supports building biologically plausible cognitive architectures.

Abstract

Cognitive map learners (CML) are a collection of separate yet collaboratively trained single-layer artificial neural networks (matrices), which navigate an abstract graph by learning internal representations of the node states, edge actions, and edge action availabilities. A consequence of this atypical segregation of information is that the CML performs near-optimal path planning between any two graph node states. However, the CML does not learn when or why to transition from one node to another. This work created CMLs with node states expressed as high dimensional vectors consistent with hyperdimensional computing (HDC), a form of symbolic machine learning (ML). This work evaluated HDC-based CMLs as ML modules, capable of receiving external inputs and computing output responses which are semantically meaningful for other HDC-based modules. Several CMLs were prepared independently then repurposed to solve the Tower of Hanoi puzzle without retraining these CMLs and without explicit reference to their respective graph topologies. This work suggests a template for building levels of biologically plausible cognitive abstraction and orchestration.