Brain-Like Processing Pathways Form in Models With Heterogeneous Experts

Jack Cook, Danyal Akarca, Rui Ponte Costa, Jascha Achterberg

Keywords: Processing pathways, Brain-inspired neural networks, Mixture-of-Experts, Modularity, Task complexity, Adaptive processing

TL;DR: Using a heterogeneous Mixture-of-Experts model architecture, we show that brain-like processing pathways form due to inductive biases on processing complexity and expert dropout

Abstract: The brain is made up of a vast set of heterogeneous regions that dynamically organize into pathways as a function of task demands. Examples of such pathways can be found in the interactions between cortical and subcortical networks during learning, or in sub-networks specializing for task characteristics such as difficulty or modality. Despite the large role these pathways play in cognition, the mechanisms through which brain regions organize into pathways remain unclear. In this work, we use an extension of the Heterogeneous Mixture-of-Experts architecture to show that heterogeneous regions do not form processing pathways by themselves, implying that the brain likely implements specific constraints which result in the reliable formation of pathways. We identify three biologically relevant inductive biases that encourage pathway formation: a routing cost imposed on the use of more complex regions, a scaling factor that reduces this cost when task performance is low, and randomized expert dropout. When comparing our resulting Mixture-of-Pathways model with the brain, we observe that the artificial pathways in our model match how the brain uses cortical and subcortical systems to learn and solve tasks of varying difficulty. In summary, we introduce a novel framework for investigating how the brain forms task-specific pathways through inductive biases, and the effects these biases have on the behavior of Mixture-of-Experts models.

Primary Area: Neuroscience and cognitive science (e.g., neural coding, brain-computer interfaces)

Submission Number: 22912