3 papers
cs.RO2026
Robot Arm Control via Cognitive Map Learners
Nathan McDonald, Colyn Seeley, Christian Brazeau
Cognitive map learners (CML) have been shown to enable hierarchical, compositional machine learning. That is, interpedently trained CML modules can be arbitrarily composed together…
cs.NE2024
Modular, Hierarchical Machine Learning for Sequential Goal Completion
Nathan McDonald
Given a maze populated with different objects, one may task a robot with a sequential goal completion task, e.g. 1) pick up a key then 2) unlock the door then 3) unlock the treasur…
cs.NE2024
Assembling Modular, Hierarchical Cognitive Map Learners with Hyperdimensional Computing
Nathan McDonald, Anthony Dematteo
Cognitive map learners (CML) are a collection of separate yet collaboratively trained single-layer artificial neural networks (matrices), which navigate an abstract graph by learni…