Keywords: branch specialization, computational vision, curriculum learning
TL;DR: Branch specialization in artificial neural networks can sometimes be predicted by the inductive bias of branches and training curricula.
Abstract: What motivates the brain to allocate tasks to different regions and what distinguishes multiple-demand brain regions and the tasks they perform from ones in highly specialized areas? Here we explore these neuroscientific questions using a purely computational framework and theoretical insights. In particular, we focus on how branches of a neural network learn representations contingent on their architecture and optimization task. We train branched neural networks on families of Gabor filters as the input training distribution and optimize them to perform combinations of angle, average color, and size approximation tasks. We find that networks predictably allocate tasks to the branches with appropriate inductive biases. However, this task-to-branch matching is not required for branch specialization, as even identical branches in a network tend to specialize. Finally, we show that branch specialization can be controlled by a curriculum in which tasks are alternated instead of jointly trained. Longer training between alternation corresponds to more even task distribution among branches, providing a possible model for multiple-demand regions in the brain.