Deep learning architecture for general cognitive control
CogPonder is a flexible, differentiable model of cognitive control inspired by the Test-Operate-Test-Exit (TOTE) architecture in psychology and the PonderNet framework in deep learning. It decouples the act of control from the controlled processes by introducing a controller that wraps around any end-to-end deep learning model. This controller decides when to terminate processing and output a response, thus producing both a response and response time.