Can the brain use waves to solve planning problems?
This work addresses how the brain might solve planning problems, potentially offering insights for neuroscience and AI, but it appears incremental as it builds on existing cognitive map theories.
The authors tackled the problem of solving graph traversal tasks, such as spatial navigation, by proposing a neural network model that uses wave-like activation patterns to guide activity from a start to a target state, achieving compatibility with empirical findings in mammalian brain regions.
A variety of behaviors like spatial navigation or bodily motion can be formulated as graph traversal problems through cognitive maps. We present a neural network model which can solve such tasks and is compatible with a broad range of empirical findings about the mammalian neocortex and hippocampus. The neurons and synaptic connections in the model represent structures that can result from self-organization into a cognitive map via Hebbian learning, i.e. into a graph in which each neuron represents a point of some abstract task-relevant manifold and the recurrent connections encode a distance metric on the manifold. Graph traversal problems are solved by wave-like activation patterns which travel through the recurrent network and guide a localized peak of activity onto a path from some starting position to a target state.