Inductive biases of neural network modularity in spatial navigation
ML @ CMU
JANUARY 2, 2025
TL;DR: The brain may have evolved a modular architecture for daily tasks, with circuits featuring functionally specialized modules that match the task structure. We hypothesize that this architecture enables better learning and generalization than architectures with less specialized modules. To test this, we trained reinforcement learning agents with various neural architectures on a naturalistic navigation task.
Let's personalize your content